© 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. 3262
    Prev
    Next
    INDEX
    Explanations

    have been

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

    The neuron activates on numeric tokens—i.e. it detects numbers and numerical data in the text.

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

    No Comments

    Negative Logits
    三個
    0.55
     wasnt
    0.52
     wasn
    0.50
    三个
    0.49
    兩個
    0.49
    쫌
    0.48
    几个
    0.46
    変更
    0.46
    ुए
    0.46
    irteen
    0.46
    POSITIVE LOGITS
     mohou
    0.41
     organizational
    0.41
     свойства
    0.41
     свойств
    0.40
     customarily
    0.40
     способны
    0.40
     dapat
    0.40
     lze
    0.40
     propiedades
    0.39
     способен
    0.39
    Activations Density 0.237%

    No Known Activations