© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103660
    Prev
    Next
    INDEX
    Explanations

    nifty

    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
    
    -2.91
    氿
    -2.70
    
    -2.64
    AISSEE
    -2.61
     gän
    -2.55
    OUTUBE
    -2.55
    Ꮉ
    -2.52
    杙
    -2.50
    ญี่ป
    -2.50
     起毛
    -2.44
    POSITIVE LOGITS
    )
    2.88
    [
    2.50
     как
    2.36
    」
    2.33
    .
    2.33
    一旁
    2.33
    :
    2.23
    ”
    2.23
    },
    2.20
     ذ
    2.20
    Activations Density 0.002%

    No Known Activations