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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81082
    Prev
    Next
    INDEX
    Explanations

    gram negative

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

    The neuron recognizes "gram" in bacteria classifications, particularly "gram-negative" and "gram-positive" in scientific or medical contexts.

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

    The neuron fires strongly on occurrences of “gram” (as in Gram-negative/Gram-positive) in bacterial classification.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Asn
    -0.74
    ͜
    -0.73
     protected
    -0.71
     unprotected
    -0.71
     Jenner
    -0.69
    basement
    -0.65
     retired
    -0.65
     Andean
    -0.64
    Tutorials
    -0.64
    badan
    -0.64
    POSITIVE LOGITS
     Chee
    0.73
     milled
    0.71
     Rodrig
    0.71
     islands
    0.69
    經歷
    0.69
     важно
    0.67
     Yards
    0.65
     Shum
    0.65
     rectangles
    0.65
     surveys
    0.64
    Activations Density 0.059%

    No Known Activations