© 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. 34-GEMMASCOPE-RES-131K
    7. 58827
    Prev
    Next
    INDEX
    Explanations

    Ohio and numbers

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

    The neuron is triggered by standalone numeric identifiers—sequences of digits like document or patent numbers and year citations.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    9
    -0.95
     девя
    -0.82
    冽
    -0.80
     faulting
    -0.79
    Whale
    -0.75
    8
    -0.75
     chín
    -0.75
     tausend
    -0.74
    duel
    -0.74
     gaunt
    -0.73
    POSITIVE LOGITS
     Forty
    1.18
     forty
    1.14
     thirty
    1.14
    3
    1.00
     Thirty
    0.97
    Forty
    0.90
    ۴
    0.81
     Bonneville
    0.79
    Thirty
    0.78
    概
    0.78
    Activations Density 0.127%

    No Known Activations