© 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. 61258
    Prev
    Next
    INDEX
    Explanations

    smoke and smoked things

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

    The neuron activates on mentions of “smoke” (e.g. smoked, smokehouse) 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_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
    啬
    -2.42
    肏
    -2.27
    糹
    -2.25
    ︕
    -2.03
    淠
    -2.03
     після
    -2.00
    .”
    -1.99
     vierten
    -1.98
    裃
    -1.98
     皇族
    -1.97
    POSITIVE LOGITS
     '
    2.36
    -
    2.13
    ("
    2.03
     een
    1.95
     «
    1.87
    [
    1.86
    a
    1.84
     shows
    1.78
     hardy
    1.74
     jetzt
    1.66
    Activations Density 0.002%

    No Known Activations