© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119009
    Prev
    Next
    INDEX
    Explanations

    member/is/expressed

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

    code syntax elements and programming language constructs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    iosa
    -0.89
     Gaelic
    -0.81
    Engineers
    -0.75
     golden
    -0.71
    Devi
    -0.71
    NEED
    -0.70
    asiun
    -0.70
     Catch
    -0.70
    NOTE
    -0.70
    Took
    -0.69
    POSITIVE LOGITS
     RESULT
    1.04
    localctx
    1.00
    putInt
    0.88
     quads
    0.81
     maybe
    0.80
    โย
    0.79
     Selva
    0.79
    ůže
    0.78
    localization
    0.78
    Попис
    0.78
    Activations Density 0.002%

    No Known Activations