© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47459
    Prev
    Next
    INDEX
    Explanations

    B-word, B&B, B-cell

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

    the letter 'B' at the beginning of names, terms, or classifications, especially when followed by a hyphen.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is keyed to spotting the token sequence “B-” (a capital B immediately followed by a hyphen).

    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
     マグ
    -1.87
     boyut
    -1.70
     pracow
    -1.70
    塒
    -1.65
     which
    -1.63
     bislang
    -1.62
     gegenwär
    -1.61
     weitgehend
    -1.61
     cihaz
    -1.59
    頽
    -1.59
    POSITIVE LOGITS
     '
    2.09
    '
    2.03
     was
    1.80
    ',
    1.75
     But
    1.73
    [
    1.69
    /
    1.67
    晾
    1.61
    *
    1.60
     =
    1.57
    Activations Density 0.034%

    No Known Activations