© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72935
    Prev
    Next
    INDEX
    Explanations

    Saturday

    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_22/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
    を始め
    -2.47
    would
    -2.44
    zijn
    -2.42
     และ
    -2.33
    鲠
    -2.28
    ܞ
    -2.20
    takings
    -2.16
    wonderful
    -2.16
    Ꮿ
    -2.16
    埽
    -2.14
    POSITIVE LOGITS
    In
    3.03
     It
    2.64
    [
    2.59
    ↵↵
    2.52
     exacting
    2.33
    (
    2.28
     sprawling
    2.22
     notwithstanding
    2.22
    B
    2.22
     Mostly
    2.19
    Activations Density 0.017%

    No Known Activations