© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71010
    Prev
    Next
    INDEX
    Explanations

    multi-lingual technical and natural language phrases

    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
    </i>
    -3.94
    </h3>
    -3.47
    ↵
    -2.77
     vorigen
    -2.61
     consequence
    -2.61
    艫
    -2.59
    </strong>
    -2.56
    </u>
    -2.55
    ⽥
    -2.53
    "},
    -2.52
    POSITIVE LOGITS
    過ごし
    2.34
    '
    2.31
    *
    2.30
    ```
    2.30
     japonais
    2.23
    卨
    2.23
    значення
    2.19
    嵓
    2.19
    るので
    2.19
     його
    2.19
    Activations Density 0.000%

    No Known Activations