© 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. 100505
    Prev
    Next
    INDEX
    Explanations

    collection prefix wrapper token samples cancel

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

    hyphens in code identifiers like class names, variable names, and file paths.

    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
     when
    -1.88
    '
    -1.79
     with
    -1.71
    小弟
    -1.55
    岌
    -1.54
     preocupación
    -1.52
     Saltar
    -1.52
    惆
    -1.49
     glimpses
    -1.47
    </tbody>
    -1.46
    POSITIVE LOGITS
    <bos>
    2.41
     gustar
    1.76
    舠
    1.75
    鯷
    1.74
    捽
    1.67
    𓆜
    1.64
    YNAMIC
    1.63
    м
    1.62
    са
    1.58
    分からない
    1.58
    Activations Density 0.134%

    No Known Activations