© 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. 102232
    Prev
    Next
    INDEX
    Explanations

    positions and titles

    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
     manguera
    -1.64
     adhesivo
    -1.61
     is
    -1.54
     znaleźć
    -1.51
     wybrać
    -1.47
     sellado
    -1.46
    炊き
    -1.46
     cálido
    -1.46
     suelos
    -1.45
     zobaczyć
    -1.45
    POSITIVE LOGITS
     for
    3.19
     in
    2.97
     of
    2.80
     a
    2.19
     sebuah
    1.82
     and
    1.80
     bahkan
    1.77
     on
    1.62
     even
    1.56
     using
    1.56
    Activations Density 0.160%

    No Known Activations