© 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. 10-GEMMASCOPE-RES-131K
    7. 15818
    Prev
    Next
    INDEX
    Explanations

    chatter, clatter, bing sounds

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

    This neuron detects onomatopoetic words for rapid or trivial speech (e.g. chatter, jabber, gabble, burble).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    迓
    -2.39
    怍
    -2.38
    峮
    -2.17
     alarme
    -2.14
    圌
    -2.13
    洐
    -2.11
    녘
    -2.08
    鹚
    -2.08
    婼
    -2.08
     saluti
    -2.08
    POSITIVE LOGITS
    \\
    2.77
    .
    2.70
    )
    2.56
    ."
    2.48
    0
    2.47
    \&
    2.36
    \%
    2.22
    ',
    2.20
    ...
    2.13
    ",
    2.11
    Activations Density 0.004%

    No Known Activations