© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13750
    Prev
    Next
    INDEX
    Explanations

    conversational greetings and closings

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

    The neuron fires on emphatic or evaluative tokens—words (and even non-word tokens) that carry strong, subjective emphasis or sentiment.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    scott
    0.69
     hickory
    0.67
    ⁃
    0.66
     Tyler
    0.65
     entirety
    0.64
     welches
    0.64
     Midwest
    0.64
     vinyl
    0.63
     steampunk
    0.63
     Scott
    0.63
    POSITIVE LOGITS
     bhai
    0.91
    ^_
    0.88
     Bhai
    0.88
     yaar
    0.83
     Alhamdulillah
    0.80
     Airtel
    0.75
    Allah
    0.75
    INDIA
    0.75
     Bachchan
    0.73
     Gandhiji
    0.73
    Activations Density 0.141%

    No Known Activations