© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13675
    Prev
    Next
    INDEX
    Explanations

    as far as

    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
    {
    -1.52
    am
    -1.45
    )}+
    -1.42
    \
    -1.41
    //
    -1.36
    ");
    -1.35
     Njema
    -1.30
    </td>
    -1.30
    ED
    -1.27
    );
    -1.25
    POSITIVE LOGITS
    </strong>
    1.63
    CHREIB
    1.34
    личные
    1.34
     espectro
    1.34
    亍
    1.33
     várias
    1.33
     richtige
    1.30
    푘
    1.30
     descrito
    1.27
     například
    1.27
    Activations Density 0.008%

    No Known Activations