© 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. 112426
    Prev
    Next
    INDEX
    Explanations

    Izmir, Nina Simone, Из каких

    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
    a
    -3.23
    D
    -2.95
    ↵
    -2.86
    ;
    -2.78
    </i>
    -2.61
    );
    -2.59
    </td>
    -2.52
    u
    -2.50
    C
    -2.45
    o
    -2.41
    POSITIVE LOGITS
    "—
    3.19
    ◆◇
    2.77
     INFORMACIÓN
    2.67
    翃
    2.67
     demokra
    2.64
     teknologi
    2.59
    The
    2.55
     charmant
    2.50
     واضح
    2.47
     nya
    2.44
    Activations Density 0.002%

    No Known Activations