© 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. 105223
    Prev
    Next
    INDEX
    Explanations

    people

    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
    rália
    -1.78
    嫫
    -1.77
    ⩴
    -1.75
    −/−
    -1.69
    lishes
    -1.68
    ༀ
    -1.58
    РАВ
    -1.55
    釤
    -1.54
     grootste
    -1.49
    髡
    -1.49
    POSITIVE LOGITS
    <b>
    1.71
    酝
    1.61
    .
    1.61
     smugglers
    1.55
     (
    1.52
    </td>
    1.52
     (!)
    1.51
    <i>
    1.51
     относится
    1.48
     [
    1.48
    Activations Density 0.007%

    No Known Activations