© 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. 79115
    Prev
    Next
    INDEX
    Explanations

    diseases and medical conditions

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

    names of infectious diseases and medical conditions.

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

    The neuron is a detector for numeric tokens or numeric expressions (e.g., years, citation numbers, magnitudes) in the text.

    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
    thyst
    -0.84
     insign
    -0.82
    ifoli
    -0.81
    onné
    -0.79
     птицы
    -0.77
    Zdra
    -0.76
    ONOM
    -0.76
    INST
    -0.76
    高手
    -0.76
    recycle
    -0.75
    POSITIVE LOGITS
     palsy
    0.84
     bends
    0.80
     Consumption
    0.79
     beri
    0.79
    GD
    0.77
     disease
    0.76
    rigo
    0.73
    hydrop
    0.73
     fever
    0.72
     contracted
    0.72
    Activations Density 0.060%

    No Known Activations