© 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. 34-GEMMASCOPE-RES-131K
    7. 79526
    Prev
    Next
    INDEX
    Explanations

    dumbwaiters, dumbfounding, numbskulls

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

    This neuron responds to occurrences of the root “dumb” (and its inflected or derived forms) in words.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sog
    -0.82
    idated
    -0.76
    tibus
    -0.71
     extraña
    -0.69
     ballast
    -0.68
    Zab
    -0.68
     enge
    -0.66
    Zones
    -0.66
     berjalan
    -0.66
    nému
    -0.66
    POSITIVE LOGITS
    struck
    1.59
    found
    1.20
    founded
    1.14
     struck
    1.06
    ell
    1.05
    dumb
    1.04
     luck
    1.04
     founded
    1.00
     dumb
    0.98
    ells
    0.89
    Activations Density 0.017%

    No Known Activations