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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 59273
    Prev
    Next
    INDEX
    Explanations

    Tokens that mark emphasis or structural importance (section headings, bolded/emphatic words, numbers/dates or other prominent markers) indicating a document's important or attention-grabbing elements.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    AY
    0.50
    .\
    0.49
    \[
    0.48
    р
    0.47
    .
    0.46
    Ta
    0.43
    呈
    0.43
    ensure
    0.42
    с
    0.42
    and
    0.42
    POSITIVE LOGITS
     demise
    0.52
     sarcasm
    0.51
     debunk
    0.50
    ග්
    0.48
     antitrust
    0.48
     내용을
    0.47
     debating
    0.46
     sarcastic
    0.46
     tweeter
    0.44
     oublier
    0.44
    Activations Density 0.000%

    No Known Activations