© 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. 8211
    Prev
    Next
    INDEX
    Explanations

    scientific community

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

    references to "the community" or specific communities (especially scientific, medical, international).

    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_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
     bonitos
    -1.98
     four
    -1.88
     two
    -1.87
    ↵
    -1.84
     eficientes
    -1.83
     three
    -1.77
     exclusivas
    -1.74
     six
    -1.69
     your
    -1.68
    ဴ
    -1.67
    POSITIVE LOGITS
    d
    1.89
    }
    1.77
    0
    1.73
    硨
    1.69
     unſ
    1.64
    ቍ
    1.62
    ’
    1.61
    詎
    1.57
    '
    1.56
    蜮
    1.55
    Activations Density 0.016%

    No Known Activations