© 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. 42410
    Prev
    Next
    INDEX
    Explanations

    size_t

    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
     Cancelar
    -1.71
     Resolución
    -1.62
    %%
    -1.60
    場の
    -1.60
    ковь
    -1.59
     Configuración
    -1.59
     and
    -1.55
     Capacidad
    -1.55
     suscripción
    -1.52
    "',
    -1.51
    POSITIVE LOGITS
    2
    1.81
    <bos>
    1.73
    スペック
    1.72
    その他の
    1.67
    のでは
    1.59
    ありがたい
    1.59
    総評
    1.57
     \
    1.56
    最新の
    1.56
    衚
    1.55
    Activations Density 0.003%

    No Known Activations