© 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. 58420
    Prev
    Next
    INDEX
    Explanations

    headlines

    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
     o
    -3.06
    {
    -2.95
     There
    -2.94
     .
    -2.86
     i
    -2.84
     —
    -2.80
    We
    -2.75
    "
    -2.70
     また
    -2.67
     -
    -2.66
    POSITIVE LOGITS
    茕
    3.67
    襌
    3.38
     měla
    2.95
    
    2.91
    檍
    2.81
     エントランス
    2.73
     abiye
    2.72
     pérd
    2.69
    鉏
    2.67
     niedersachsen
    2.66
    Activations Density 0.004%

    No Known Activations