© 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. 13911
    Prev
    Next
    INDEX
    Explanations

    can easily use

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

    The neuron activates on floating‐point numeric tokens (decimal numbers) in the text.

    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
     Rating
    0.66
     czyli
    0.59
     পুত্রের
    0.57
     Probability
    0.56
    ∴
    0.55
     przykład
    0.54
     ÷
    0.54
     கொடுத்து
    0.54
    ieth
    0.53
     índice
    0.53
    POSITIVE LOGITS
    大規模
    0.70
    大规模
    0.61
    េង
    0.59
    टन
    0.59
     collaborating
    0.59
    Environ
    0.59
    getExternal
    0.59
    네
    0.58
    নে
    0.58
    বিষ্য
    0.57
    Activations Density 0.000%

    No Known Activations