© 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. 38474
    Prev
    Next
    INDEX
    Explanations

    done

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

    The neuron fires on occurrences of the word “done” (e.g. as a UI button label or in quotes to mark completion).

    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
     the
    -1.84
    柺
    -1.79
    -1.79
     следующие
    -1.77
     waren
    -1.74
     дополнительные
    -1.73
     jopa
    -1.69
     \
    -1.66
    冧
    -1.64
     frucht
    -1.60
    POSITIVE LOGITS
    $
    2.27
     done
    1.87
    In
    1.67
     fashioned
    1.63
    Done
    1.62
    The
    1.61
    DONE
    1.57
     DONE
    1.55
    カス
    1.55
     accusing
    1.53
    Activations Density 0.014%

    No Known Activations