© 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. 143793
    Prev
    Next
    INDEX
    Explanations

    my skill

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

    anyone else

    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
    rels
    0.46
    銛
    0.45
     उबाल
    0.44
    堤
    0.44
    料理
    0.44
    付款
    0.44
    分子
    0.43
    imente
    0.43
    槁
    0.43
     Deps
    0.42
    POSITIVE LOGITS
     Werte
    0.59
     અવ
    0.46
     നേര
    0.46
     authorizing
    0.46
     IntegerValue
    0.46
     getDateTime
    0.45
     prematurely
    0.45
     वेरिएबल
    0.44
     waarop
    0.44
     अवर
    0.44
    Activations Density 0.000%

    No Known Activations