© 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. 43418
    Prev
    Next
    INDEX
    Explanations

    adult content requests

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

    Short function tokens or punctuation marks that appear in technical contexts, including code snippets, structured data formats (JSON, SQL), and formal documentation, often serving as syntax elements or delimiters.

    eleuther_acts_top20 · 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
     Gora
    0.34
     bizim
    0.33
    arek
    0.33
     ihm
    0.33
     biraz
    0.33
     eil
    0.31
    emir
    0.31
    ăl
    0.31
     nein
    0.31
     पेर
    0.31
    POSITIVE LOGITS
    लेकिन
    0.37
     എന്നതാണ്
    0.35
    보다
    0.34
    σετε
    0.34
    того
    0.34
     влияет
    0.34
    줘야
    0.34
    𝙩
    0.33
    dsale
    0.33
    쌉
    0.33
    Activations Density 0.068%

    No Known Activations