© 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. 14234
    Prev
    Next
    INDEX
    Explanations

    previous names

    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
     possibilités
    -1.69
     critères
    -1.64
     canaux
    -1.56
     Diseño
    -1.52
     lesquelles
    -1.51
     rojos
    -1.48
    镲
    -1.47
    鷽
    -1.47
     disponibilités
    -1.46
     connaissent
    -1.46
    POSITIVE LOGITS
     more
    2.09
     to
    2.05
     but
    2.03
     from
    1.95
     without
    1.88
     by
    1.74
     of
    1.74
     in
    1.63
    from
    1.62
     as
    1.57
    Activations Density 0.062%

    No Known Activations