© 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. 70671
    Prev
    Next
    INDEX
    Explanations

    right in the middle

    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
    \
    -1.97
     OGSÅ
    -1.89
    ÑOS
    -1.88
     of
    -1.82
    >
    -1.81
    .
    -1.79
    1
    -1.66
    </em>
    -1.65
    three
    -1.64
    <td>
    -1.63
    POSITIVE LOGITS
     also
    2.11
     betek
    2.02
    灬
    1.77
    ühlen
    1.76
    愎
    1.69
     it
    1.67
     bordering
    1.64
    碌
    1.61
    zędu
    1.59
     capacidad
    1.59
    Activations Density 0.006%

    No Known Activations