© 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. 10-GEMMASCOPE-RES-131K
    7. 8109
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -0.90
    ∴
    -0.90
    姉
    -0.87
    SUPER
    -0.86
    0
    -0.86
     سوف
    -0.85
    ,
    -0.85
    ()).
    -0.84
    ärme
    -0.84
    I
    -0.84
    POSITIVE LOGITS
    StoryboardSegue
    1.15
    laquo
    1.14
    🧛
    1.00
    elter
    0.97
     življen
    0.96
     餐廳
    0.96
    㩒
    0.94
    ുന്നു
    0.94
    getYear
    0.92
    getFullYear
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.