© 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. 41062
    Prev
    Next
    INDEX
    Explanations

    off-road and on-road vehicles

    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
    </h2>
    -2.02
    </td>
    -2.02
    那时
    -1.93
    鹀
    -1.87
     Saltar
    -1.86
     =
    -1.82
    ];
    -1.82
    してました
    -1.77
     ",";
    -1.75
     είναι
    -1.74
    POSITIVE LOGITS
     '
    2.31
     hermosos
    2.03
     alguns
    2.02
    LETON
    2.00
    𐐀
    1.99
    龊
    1.98
     uniquement
    1.96
     divinely
    1.95
     maravill
    1.95
    、“
    1.94
    Activations Density 0.004%

    No Known Activations