© 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. 119942
    Prev
    Next
    INDEX
    Explanations

    part of

    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
     кілька
    -2.08
     pegatina
    -1.94
     prestaciones
    -1.91
     Resolución
    -1.79
     obligaciones
    -1.76
     powietrza
    -1.73
     Condiciones
    -1.73
     czuj
    -1.71
     acabamento
    -1.71
     Reglas
    -1.69
    POSITIVE LOGITS
     of
    5.16
     or
    2.64
     on
    2.25
     it
    2.22
     that
    2.03
     at
    1.88
     some
    1.82
     its
    1.80
     by
    1.79
     even
    1.74
    Activations Density 0.584%

    No Known Activations