© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111992
    Prev
    Next
    INDEX
    Explanations

    first or second instance

    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
     for
    -1.63
     during
    -1.48
     when
    -1.48
     only
    -1.48
     because
    -1.47
     However
    -1.47
     Surprisingly
    -1.46
     Because
    -1.41
     According
    -1.40
     where
    -1.38
    POSITIVE LOGITS
     orec
    1.52
     rôles
    1.38
     arriver
    1.34
    艄
    1.31
     projets
    1.31
    ｈ
    1.30
    يتم
    1.30
     strani
    1.29
    intended
    1.29
    instead
    1.29
    Activations Density 0.073%

    No Known Activations