© 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. 96904
    Prev
    Next
    INDEX
    Explanations

    essay topics and descriptions

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

    rules and procedures

    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
    ch
    0.52
    allow
    0.51
    ink
    0.46
    G
    0.46
    cht
    0.45
    ្វ
    0.45
    kult
    0.45
    in
    0.45
    mg
    0.45
    kub
    0.45
    POSITIVE LOGITS
     виправи
    0.52
     ∈
    0.52
     Django
    0.50
     acquies
    0.49
     Djibouti
    0.49
     Sval
    0.49
     Warzone
    0.49
    スムーズ
    0.48
     upravo
    0.48
     नाबालिग
    0.48
    Activations Density 0.000%

    No Known Activations