© 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. 4945
    Prev
    Next
    INDEX
    Explanations

    joke about crossing

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

    The main thing this neuron does is detect passages densely packed with numeric or quantitative data (e.g. conversion rates, percentages, values, statistics).

    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
     inflationary
    0.61
     inflation
    0.61
     ли
    0.59
     inflación
    0.58
     remedy
    0.57
    blichen
    0.56
     Guth
    0.55
     inflate
    0.55
    getJSONObject
    0.54
     ਐ
    0.54
    POSITIVE LOGITS
    Want
    0.73
    Interested
    0.71
    Looking
    0.60
    Below
    0.59
    Sometimes
    0.58
    サイト
    0.58
     Want
    0.57
    want
    0.57
    Sharing
    0.56
    Estim
    0.56
    Activations Density 0.006%

    No Known Activations