© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13829
    Prev
    Next
    INDEX
    Explanations

    lists with counts or definitions

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

    The neuron is activated by numeric tokens (counts, measurements, dates, dimensions, statistical figures, etc.), i.e. any standalone number or numeric expression.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    क्ष्म
    0.54
     Other
    0.53
    非
    0.52
     мест
    0.50
    소년
    0.50
    🪁
    0.50
    격
    0.49
    пок
    0.49
    debounce
    0.49
    懵
    0.48
    POSITIVE LOGITS
     vacc
    0.68
     vacu
    0.63
     genus
    0.61
     churn
    0.59
     سطح
    0.57
     problems
    0.57
    ér
    0.57
     produkty
    0.57
     snakes
    0.56
    စိတ်အပိုင်း
    0.56
    Activations Density 0.000%

    No Known Activations