© 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. 103307
    Prev
    Next
    INDEX
    Explanations

    intelligibility and readability

    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
    them
    -1.92
     могут
    -1.90
    these
    -1.89
     cristianos
    -1.82
    瑒
    -1.78
    ￬
    -1.77
    they
    -1.77
    enablog
    -1.74
     của
    -1.70
    ON
    -1.70
    POSITIVE LOGITS
    0
    1.86
    \&
    1.73
     Lingkungan
    1.63
    .");
    1.53
    jadikan
    1.51
     for
    1.49
     剧照
    1.49
    ложении
    1.48
    tojas
    1.48
     巻き
    1.46
    Activations Density 0.013%

    No Known Activations