© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102722
    Prev
    Next
    INDEX
    Explanations

    glitch, bleep, blurb, blemish

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

    The neuron selectively fires on onomatopoeic sound-effect words (e.g. “blip,” “bleep,” “glitch,” etc.).

    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
    .“
    -2.03
     Valuable
    -2.02
    姈
    -1.98
    場合は
    -1.98
    蟶
    -1.95
    毟
    -1.91
    餬
    -1.91
    ֎
    -1.91
    
    -1.91
     SearchView
    -1.89
    POSITIVE LOGITS
    '
    3.11
    [
    2.56
    h
    2.31
    {
    2.30
    (
    2.27
    //
    2.14
     "
    2.06
     in
    2.00
     le
    1.89
    else
    1.83
    Activations Density 0.007%

    No Known Activations