© 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. 60804
    Prev
    Next
    INDEX
    Explanations

    maintaining or maintenance

    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
    蛱
    -2.06
     três
    -2.02
    鼍
    -1.98
     wysokość
    -1.97
    鸶
    -1.96
    蠖
    -1.94
    凩
    -1.92
    㐂
    -1.87
     inny
    -1.86
    蹰
    -1.84
    POSITIVE LOGITS
    </i>
    2.11
    <b>
    1.85
    </td>
    1.83
    in
    1.77
    p
    1.73
    f
    1.72
    d
    1.70
    m
    1.58
    b
    1.56
    '
    1.52
    Activations Density 0.023%

    No Known Activations