© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3858
    Prev
    Next
    INDEX
    Explanations

    code examples with separators

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

    This neuron detects numeric tokens that include decimal points (floating-point numbers).

    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_24_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
    .
    0.55
    ?
    0.53
    (
    0.52
    -
    0.47
    /
    0.46
    '
    0.45
    ...
    0.44
    able
    0.43
    DA
    0.41
    TV
    0.40
    POSITIVE LOGITS
     学習
    0.55
    ෲ
    0.52
     ลอง
    0.52
    ቒ
    0.51
     初始化
    0.50
     結婚
    0.50
     เรียน
    0.49
     ܗ
    0.49
     Многие
    0.49
    ቝ
    0.49
    Activations Density 0.000%

    No Known Activations