© 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. 65
    Prev
    Next
    INDEX
    Explanations

    interesting followed by a noun

    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
    In
    -1.82
     We
    -1.72
     Our
    -1.70
    --
    -1.64
    2
    -1.63
    8
    -1.57
    .
    -1.55
     häufigsten
    -1.54
    [
    -1.48
     полноцен
    -1.46
    POSITIVE LOGITS
    henswürdigkeiten
    1.76
    雋
    1.68
     costuras
    1.68
     paille
    1.59
     but
    1.56
    »,
    1.55
     vähän
    1.55
     endDate
    1.52
     decorar
    1.50
     []:
    1.48
    Activations Density 0.023%

    No Known Activations