© 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. 41209
    Prev
    Next
    INDEX
    Explanations

    work at

    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
    ).
    -2.31
    ༔
    -1.91
    𓆸
    -1.90
     丁目
    -1.79
     }),
    -1.78
     titulada
    -1.77
    ᯾
    -1.76
    颡
    -1.75
    мне
    -1.74
    {
    -1.73
    POSITIVE LOGITS
    ↵↵
    2.14
    OS
    1.96
    k
    1.95
    ES
    1.92
    或
    1.86
    1.84
    需要
    1.83
    OD
    1.80
    OR
    1.77
    IT
    1.76
    Activations Density 0.004%

    No Known Activations