© 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. 10-GEMMASCOPE-RES-131K
    7. 21318
    Prev
    Next
    INDEX
    Explanations

    young or less

    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
    逦
    -2.23
    </strong>
    -2.13
    蚣
    -1.95
    onsors
    -1.80
    striker
    -1.79
    olkien
    -1.73
    phonie
    -1.72
    apatalk
    -1.70
    мку
    -1.68
    aneers
    -1.67
    POSITIVE LOGITS
    2.44
    </td>
    2.36
    [
    1.97
    l
    1.83
    t
    1.77
     vogliono
    1.71
    ol
    1.70
    _
    1.69
    每一个
    1.67
    裥
    1.67
    Activations Density 0.004%
    No Known Activations