© 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. 74409
    Prev
    Next
    INDEX
    Explanations

    first degree

    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
     anunció
    -1.91
    -
    -1.61
    )";
    -1.53
     stellen
    -1.53
     («
    -1.52
     AMAZING
    -1.50
     😍
    -1.49
    </h3>
    -1.48
     avec
    -1.48
    POSITIVE LOGITS
     two
    1.89
     relatively
    1.80
     three
    1.79
     provide
    1.77
     four
    1.71
     first
    1.70
     것입니다
    1.69
    ַּ
    1.69
     deciso
    1.68
     fourth
    1.65
    Activations Density 0.034%

    No Known Activations