© 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. 69810
    Prev
    Next
    INDEX
    Explanations

    urls starting with http or www

    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
    這種
    -1.93
    TextEditing
    -1.73
    If
    -1.69
    æring
    -1.69
    言えば
    -1.67
    另一
    -1.67
     コーヒー
    -1.65
    睺
    -1.65
    话说
    -1.64
     '/')
    -1.62
    POSITIVE LOGITS
     of
    2.22
     \
    1.74
    步伐
    1.56
     treinta
    1.56
     distinguishable
    1.56
     fervent
    1.52
    剌
    1.52
    镔
    1.49
    ניתן
    1.49
     pretend
    1.46
    Activations Density 0.003%

    No Known Activations