© 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. 84658
    Prev
    Next
    INDEX
    Explanations

    therapeutic agents

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

    This neuron identifies commas that precede explanatory information or context about potential risks, concerns, or biological conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires most strongly on words denoting hazards or adverse conditions (e.g. “toxic,” “explosive,” “stress event,” “resistance”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     bahkan
    -1.63
    
    -1.59
     creativos
    -1.55
    ments
    -1.55
     глав
    -1.50
    )$,
    -1.50
     coloridos
    -1.48
    ⁍
    -1.45
    èvent
    -1.42
     domésticos
    -1.41
    POSITIVE LOGITS
     then
    2.13
     which
    1.95
    1
    1.67
     next
    1.66
     instead
    1.65
     remainder
    1.59
     resulting
    1.56
    怍
    1.55
     their
    1.54
    0
    1.52
    Activations Density 0.074%

    No Known Activations