© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218157
    Prev
    Next
    INDEX
    Explanations

    all other

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

    understanding context and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     storing
    0.44
     хра
    0.43
    name
    0.43
     verhind
    0.43
    كن
    0.43
     installing
    0.42
    我们也
    0.42
    呻
    0.42
     jeopard
    0.41
     letting
    0.41
    POSITIVE LOGITS
    ဖြစ်သည်။
    0.45
    æld
    0.44
    mPreview
    0.42
    >.
    0.42
    слава
    0.42
    theoretic
    0.42
     championed
    0.42
    валася
    0.42
    amini
    0.41
     Trailer
    0.41
    Activations Density 0.000%

    No Known Activations