© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64438
    Prev
    Next
    INDEX
    Explanations

    questions and interjections

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

    The neuron flags high-intensity exclamatory tokens—interjections or swear/emotional outbursts (e.g. “wow,” “oh gosh/golly,” “fuck,” “nuh uh”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     thing
    -0.96
     scris
    -0.84
     хорошее
    -0.81
     estimate
    -0.81
    hehe
    -0.80
     criterion
    -0.79
     ggf
    -0.79
     even
    -0.79
    rzej
    -0.79
    obile
    -0.78
    POSITIVE LOGITS
    ALLEL
    0.95
    ých
    0.90
    。
    0.86
    이다
    0.86
     '#
    0.85
    因果
    0.84
     emphatically
    0.83
     predecessors
    0.83
     postIndex
    0.83
    不过是
    0.82
    Activations Density 0.028%

    No Known Activations