© 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. 7372
    Prev
    Next
    INDEX
    Explanations

    first instance of an occurrence

    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
     procedentes
    -1.94
     крайне
    -1.93
    EVERY
    -1.70
     cuidadosamente
    -1.69
     nécess
    -1.69
    彼女は
    -1.69
     literalmente
    -1.69
     visites
    -1.67
     startet
    -1.60
    fting
    -1.58
    POSITIVE LOGITS
     in
    2.16
     of
    1.93
     won
    1.61
    さんの
    1.59
     can
    1.56
    。”
    1.54
     noticed
    1.48
     riuscito
    1.46
     by
    1.45
     ensured
    1.45
    Activations Density 0.034%

    No Known Activations