© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85234
    Prev
    Next
    INDEX
    Explanations

    April is full

    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
     trajets
    -2.02
    麃
    -1.84
    these
    -1.76
    蛲
    -1.75
     komfor
    -1.70
     secteurs
    -1.68
     kanton
    -1.68
     venant
    -1.66
     chambres
    -1.66
     stadion
    -1.66
    POSITIVE LOGITS
     in
    2.27
     as
    1.93
    婚礼
    1.86
     on
    1.84
     by
    1.79
     concerning
    1.79
    の魅力
    1.79
    Donativos
    1.77
    ),
    1.75
     a
    1.74
    Activations Density 0.004%

    No Known Activations