© 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. 48315
    Prev
    Next
    INDEX
    Explanations

    breakaway territories and titles

    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
    嘥
    -2.25
     bardak
    -2.16
     mães
    -2.14
    ᠌
    -2.11
     kapak
    -1.98
     affari
    -1.94
     peggio
    -1.94
     çay
    -1.89
     intervento
    -1.88
    書いた
    -1.88
    POSITIVE LOGITS
    '
    2.47
    Ⴀ
    1.90
     They
    1.78
    ان
    1.73
    :
    1.73
    %
    1.70
    ’
    1.70
     forskjellige
    1.68
    <i>
    1.63
    ARROLLO
    1.60
    Activations Density 0.003%

    No Known Activations