© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14292
    Prev
    Next
    INDEX
    Explanations

    significance followed by colon

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

    The neuron strongly activates on standalone numeric tokens (and numeric sequences like times, dates, scores, and 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_24_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
    ется
    0.75
    лт
    0.71
    ну
    0.71
    Type
    0.69
    нено
    0.66
    ч
    0.66
    ні
    0.66
    方向
    0.65
    гать
    0.65
    не
    0.64
    POSITIVE LOGITS
    這
    0.86
     Согласно
    0.85
    ’:
    0.84
    :,
    0.81
    ፦
    0.79
     つい
    0.79
    据悉
    0.79
    ,’
    0.78
     сражение
    0.77
     दरम्यान
    0.77
    Activations Density 3.751%

    No Known Activations