© 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. 22-GEMMASCOPE-RES-131K
    7. 12515
    Prev
    Next
    INDEX
    Explanations

    string data types

    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
     các
    -1.03
    with
    -1.02
    お楽しみに
    -1.00
    際に
    -0.95
    strSql
    -0.94
    //
    -0.93
    дарь
    -0.92
     iliş
    -0.91
     misteriosa
    -0.90
    灰
    -0.90
    POSITIVE LOGITS
     posesión
    1.09
    鉺
    1.03
    </table>
    1.00
    atique
    0.99
    褰
    0.97
    ٩
    0.96
    ograf
    0.95
    もあって
    0.95
     paneles
    0.94
    LÄ
    0.94
    Activations Density 0.011%

    No Known Activations