© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18936
    Prev
    Next
    INDEX
    Explanations

    words within parentheses

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

    parentheses or code notation

    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
    ൻ
    0.50
     fah
    0.48
    加坡
    0.47
     让
    0.46
     oh
    0.45
     expiration
    0.44
    싯
    0.44
     Out
    0.44
     时间
    0.42
     perkembangan
    0.42
    POSITIVE LOGITS
    ^{-}
    0.43
     अन्यथा
    0.43
     (-\
    0.42
     substituents
    0.41
     एनिमल
    0.41
    豸
    0.41
    êt
    0.40
     -\
    0.40
     fillets
    0.40
    .""
    0.39
    Activations Density 0.000%

    No Known Activations