© 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. 14960
    Prev
    Next
    INDEX
    Explanations

    python interpreter versions

    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_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
    跸
    -2.50
    瑨
    -2.42
    内的
    -2.42
     unſ
    -2.41
    全都
    -2.30
    铪
    -2.28
    ранее
    -2.25
    
    -2.25
    u
    -2.25
    拓展
    -2.19
    POSITIVE LOGITS
    .
    3.89
     твое
    2.89
    姈
    2.86
    給你
    2.53
    The
    2.53
    愛情
    2.50
    𓋼
    2.48
    牁
    2.47
    蹌
    2.45
     gän
    2.36
    Activations Density 0.013%

    No Known Activations