© 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. 62559
    Prev
    Next
    INDEX
    Explanations

    bark or berk names

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

    The neuron fires on occurrences of the letter sequence “bark” (in names like Barker, Barkly, Barksdale, or the word bark).

    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
    rillo
    -0.75
     realizes
    -0.75
     practise
    -0.75
     sehingga
    -0.75
     quanto
    -0.73
    ggbb
    -0.72
    elfde
    -0.70
     Ва
    -0.68
     scrub
    -0.66
    moor
    -0.66
    POSITIVE LOGITS
     Bark
    0.92
    Bark
    0.84
     Ghi
    0.79
    bark
    0.78
     webinar
    0.78
     コミック
    0.74
    RTS
    0.73
    벚
    0.71
    럿
    0.71
     pí
    0.70
    Activations Density 0.022%

    No Known Activations