© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6832
    Prev
    Next
    INDEX
    Explanations

    color definitions and UI elements

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

    The neuron strongly activates on numeric tokens containing decimal points (i.e. floating-point literals) in code.

    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
     groovy
    0.57
    ("/{
    0.57
    มาก
    0.56
    嘛
    0.55
     pyl
    0.54
     (...
    0.54
     ->
    0.54
     을
    0.54
    Mixin
    0.54
    Enumerator
    0.53
    POSITIVE LOGITS
    नाचा
    0.61
    タリア
    0.60
    pecial
    0.59
    administered
    0.57
    ارين
    0.54
    घाडी
    0.53
    Innov
    0.53
    नाला
    0.53
    heds
    0.52
    णाला
    0.51
    Activations Density 0.000%

    No Known Activations