© 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. 10-GEMMASCOPE-RES-131K
    7. 9310
    Prev
    Next
    INDEX
    Explanations

    SPECT study medical

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

    The neuron activates for the phrase "Never have" which appears to be detecting negation statements about past experiences.

    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_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
    勠
    -3.47
    庒
    -3.06
     itſelf
    -2.89
    푣
    -2.86
    m
    -2.84
    喁
    -2.84
    Ꮵ
    -2.80
     插画
    -2.73
    踽
    -2.64
    锱
    -2.64
    POSITIVE LOGITS
     he
    2.86
     
    2.61
    ↵↵
    2.09
     else
    2.08
    が少ない
    2.05
    特有
    2.00
     Some
    1.99
    衣装
    1.95
    海道
    1.95
     Either
    1.95
    Activations Density 0.000%

    No Known Activations