© 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. 34-GEMMASCOPE-RES-131K
    7. 57182
    Prev
    Next
    INDEX
    Explanations

    steroids and bile acids

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

    chemical names and compounds, particularly bile-related terms and steroids.

    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
    复合
    -0.78
    ijen
    -0.75
     satunya
    -0.73
    름
    -0.72
     vassal
    -0.70
    zor
    -0.69
    xymatrix
    -0.69
    dR
    -0.69
    stwie
    -0.69
    ót
    -0.69
    POSITIVE LOGITS
     bile
    1.30
    bile
    1.09
     Bile
    0.94
     urso
    0.91
     шапка
    0.84
     Cholesterol
    0.82
    cho
    0.81
    熊
    0.81
     cholesterol
    0.80
    }',
    0.78
    Activations Density 0.142%

    No Known Activations