© 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. 84510
    Prev
    Next
    INDEX
    Explanations

    and followed by adjectives

    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
     égard
    -2.03
     of
    -1.96
     pérd
    -1.93
    籏
    -1.93
    for
    -1.93
     the
    -1.91
    fillment
    -1.89
    秶
    -1.89
     consentement
    -1.84
    漼
    -1.82
    POSITIVE LOGITS
     profundas
    1.80
     consideradas
    1.77
     focused
    1.77
     preparado
    1.75
     景色
    1.66
     тоже
    1.66
     eficientes
    1.66
     Kriege
    1.64
     and
    1.62
    *
    1.62
    Activations Density 0.268%

    No Known Activations