© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3222
    Prev
    Next
    INDEX
    Explanations

    array methods and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ث
    -0.84
     combineReducers
    -0.77
     baweł
    -0.75
    Serial
    -0.75
    メーター
    -0.74
    турой
    -0.71
    ໄ
    -0.71
     Gerä
    -0.70
    ัย
    -0.70
     logically
    -0.70
    POSITIVE LOGITS
    cert
    0.86
    Ⅰ
    0.82
     NEEDED
    0.79
    եմ
    0.77
    钢琴
    0.75
    不大
    0.74
     cert
    0.73
    etzung
    0.71
    eful
    0.69
    ₈
    0.69
    Activations Density 0.046%

    No Known Activations