© 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. 80626
    Prev
    Next
    INDEX
    Explanations

    code following dots

    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
     on
    -2.50
     as
    -2.19
     with
    -2.16
     before
    -1.88
     because
    -1.84
     in
    -1.70
     so
    -1.67
     after
    -1.65
     if
    -1.63
     even
    -1.58
    POSITIVE LOGITS
    鹩
    1.90
    枼
    1.78
     ridiculously
    1.78
    actéristi
    1.73
    having
    1.72
    ⚌
    1.70
    赑
    1.69
     ocorrer
    1.68
     нынеш
    1.68
     ludicrous
    1.65
    Activations Density 0.172%

    No Known Activations