© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60933
    Prev
    Next
    INDEX
    Explanations

    addressing the reader

    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
     you
    -2.31
    翃
    -1.98
    Awal
    -1.98
    镚
    -1.91
     можете
    -1.90
    Wady
    -1.90
    部は
    -1.88
     debes
    -1.82
     рекомендую
    -1.79
    special
    -1.77
    POSITIVE LOGITS
     to
    3.11
     It
    2.81
     on
    2.27
     during
    2.20
     as
    2.16
     in
    2.09
     into
    2.09
     This
    2.09
     from
    2.08
     for
    1.91
    Activations Density 0.280%

    No Known Activations