© 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. 102857
    Prev
    Next
    INDEX
    Explanations

    names, technical terms, and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite

    the name "Kerry" or words containing the letter sequence "ker".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    
    -3.39
     they
    -3.30
    嘥
    -2.69
     และ
    -2.63
    癰
    -2.56
    の方に
    -2.53
    蚨
    -2.52
    については
    -2.48
     favoritas
    -2.48
    𓐍
    -2.47
    POSITIVE LOGITS
    ↵↵
    3.78
    .
    2.94
    they
    2.83
    -
    2.75
    ні
    2.44
    ```
    2.42
    3
    2.38
    </td>
    2.22
    what
    2.22
    This
    2.20
    Activations Density 0.002%

    No Known Activations