© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59992
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or quotes

    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
    {
    -2.56
    -
    -2.44
    and
    -2.27
    _
    -2.20
     a
    -2.13
    >
    -2.11
    Should
    -2.05
    providedIn
    -2.00
    *
    -2.00
    (
    -1.95
    POSITIVE LOGITS
     těch
    2.28
    赑
    2.25
    ↵↵
    2.17
    )|^{
    2.16
     continúas
    2.14
     nació
    2.09
    (");
    2.08
    ()");
    2.05
    луйста
    2.03
     它
    2.03
    Activations Density 0.060%

    No Known Activations