© 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. 20513
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by non-English or special characters

    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
    -
    -3.73
    </em>
    -3.33
     of
    -3.27
     is
    -3.03
     et
    -2.98
    ).
    -2.91
     '
    -2.89
    </h4>
    -2.84
    *
    -2.75
    ↵
    -2.73
    POSITIVE LOGITS
    睒
    2.86
    erweise
    2.78
    Ꮵ
    2.66
    ᖃ
    2.61
     サロン
    2.59
    Zubereitung
    2.55
    刧
    2.50
    錼
    2.48
     nuovamente
    2.47
    猻
    2.44
    Activations Density 0.003%

    No Known Activations