© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53208
    Prev
    Next
    INDEX
    Explanations

    states and exclusions

    np_acts-logits-general · gemini-2.5-flash-lite

    Tokens that are part of formatted metadata, structural markers, or technical identifiers in text, including punctuation that delineates format elements (colons, angle brackets, quotation marks), date/time components, proper nouns in titles or headings, and formatting indicators that establish document structure rather than contributing to the main narrative content.

    eleuther_acts_top20 · claude-4-5-sonnetTriggered by @jamesnaruto04

    elements of formal news article or report formatting, including proper nouns, location names, attribution verbs, and structural markers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jamesnaruto04
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     like
    0.51
     want
    0.49
    attha
    0.46
     একটা
    0.46
     нужно
    0.46
     vreau
    0.45
     walkable
    0.45
     BOARDSIZE
    0.45
     thinking
    0.44
     outlook
    0.44
    POSITIVE LOGITS
     ██
    0.63
     regretted
    0.52
    ██
    0.49
     જણાવ્યું
    0.49
     قالت
    0.46
     ಇಂದು
    0.46
     вчера
    0.45
     blijkt
    0.44
    本日
    0.44
     regrett
    0.43
    Activations Density 0.088%

    No Known Activations