© 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. 48127
    Prev
    Next
    INDEX
    Explanations

    location and context

    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
    -1.66
    </h4>
    -1.59
     follows
    -1.52
     óculos
    -1.48
    </b>
    -1.48
    agliari
    -1.45
    挲
    -1.45
    $}
    -1.42
     cebola
    -1.41
     restauración
    -1.40
    POSITIVE LOGITS
    0
    1.61
     that
    1.56
     you
    1.48
     unless
    1.41
     unſ
    1.35
     to
    1.32
     空港
    1.30
    Wady
    1.30
     which
    1.28
    7
    1.27
    Activations Density 0.000%

    No Known Activations