© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111581
    Prev
    Next
    INDEX
    Explanations

    nicotine

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

    words and terms related to nicotine.

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of the chemical “nicotine.”

    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
     –
    -3.45
    {
    -3.20
    ’
    -3.08
    (
    -2.83
    ,
    -2.81
    
    -2.50
    /
    -2.42
     ‘
    -2.31
    The
    -2.23
     menyen
    -2.17
    POSITIVE LOGITS
    鋮
    2.27
     Когда
    2.23
     alkoholu
    2.17
     tries
    2.16
     When
    2.16
     ͡°)
    2.14
    ⌵
    2.11
    ydın
    2.11
    ͈
    2.09
    ڰ
    2.06
    Activations Density 0.003%

    No Known Activations