© 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. 13786
    Prev
    Next
    INDEX
    Explanations

    committee mentions

    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
     was
    -2.52
    栳
    -2.47
    价格
    -2.47
    窳
    -2.33
    婞
    -2.25
     outspoken
    -2.19
     inextrica
    -2.19
     они
    -2.19
     offer
    -2.16
    霓
    -2.14
    POSITIVE LOGITS
    '
    3.05
    肏
    2.86
    </sub>
    2.86
    the
    2.83
    </h3>
    2.77
    それにしても
    2.70
    哢
    2.64
    </th>
    2.64
    うーん
    2.58
    ܜ
    2.50
    Activations Density 0.004%

    No Known Activations