© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7296
    Prev
    Next
    INDEX
    Explanations

    blindness and visual impairment

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

    references to blindness or visual impairment in medical and scientific contexts.

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

    The neuron primarily detects numeric tokens (e.g., years, counts, percentages, and other numbers).

    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
    isse
    -0.85
    𝐱
    -0.81
    痧
    -0.68
    Yii
    -0.68
    radora
    -0.68
     thermometer
    -0.67
    INFIN
    -0.67
    fused
    -0.67
    QByteArray
    -0.67
     frowned
    -0.66
    POSITIVE LOGITS
     blind
    4.50
     blindness
    4.28
    blind
    4.06
     Blind
    4.00
    Blind
    3.86
    盲
    2.77
     blinded
    2.75
     sighted
    2.56
     sight
    2.45
     aveug
    2.45
    Activations Density 0.077%

    No Known Activations