© 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. 13096
    Prev
    Next
    INDEX
    Explanations

    pluck, snatch, yank, Wren

    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
    }$
    -3.59
    </strong>
    -3.22
    蛧
    -2.59
    We
    -2.47
     Portugu
    -2.44
     lega
    -2.31
    ar
    -2.31
    咔嚓
    -2.30
    </sub>
    -2.28
    It
    -2.27
    POSITIVE LOGITS
    ).
    2.31
     erwäh
    2.28
    笮
    2.23
    沨
    2.17
     considéré
    2.14
    摭
    2.11
    有好
    2.08
     город
    2.06
    出来的
    2.05
    鄜
    2.05
    Activations Density 0.003%

    No Known Activations