© 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. 2225
    Prev
    Next
    INDEX
    Explanations

    model

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

    The neuron strongly activates on high-precision numeric tokens (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_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
     cómod
    0.65
     fácil
    0.55
    ВС
    0.54
     selectInput
    0.53
    ="";
    0.50
    ={"
    0.49
     посту
    0.49
    뚤
    0.49
     водо
    0.49
     dp
    0.48
    POSITIVE LOGITS
    苑
    0.59
    டியான
    0.57
    azine
    0.57
     Complete
    0.57
     Subject
    0.57
     Terri
    0.57
    Complete
    0.57
    峽
    0.57
    Subject
    0.56
    Student
    0.55
    Activations Density 0.011%

    No Known Activations