© 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. 101523
    Prev
    Next
    INDEX
    Explanations

    locations and institutions

    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
    <bos>
    -1.87
     peluche
    -1.78
     perles
    -1.66
     tortura
    -1.63
     identifiant
    -1.61
    躥
    -1.61
    COMO
    -1.60
     lavable
    -1.60
     plafon
    -1.59
     diamants
    -1.59
    POSITIVE LOGITS
     of
    3.30
     to
    2.28
     but
    2.19
     from
    2.02
     like
    1.87
     From
    1.81
     all
    1.73
     there
    1.71
     bernama
    1.63
     their
    1.59
    Activations Density 0.039%

    No Known Activations