© 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. 9826
    Prev
    Next
    INDEX
    Explanations

    professional involvement

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

    This neuron specializes in detecting standalone numeric tokens with decimal points (i.e. floating‐point numbers) in the text.

    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
     коды
    0.78
     #{
    0.74
     годы
    0.74
    #{
    0.73
    [{
    0.72
    ﻝ
    0.71
    <0xB8>
    0.70
    代
    0.70
     выпла
    0.69
    一些
    0.68
    POSITIVE LOGITS
    jenigen
    0.82
    ্স
    0.81
    c
    0.81
    িক
    0.79
    क्यू
    0.79
    </h2>
    0.79
     sien
    0.78
    ický
    0.77
    عي
    0.76
     smě
    0.76
    Activations Density 0.000%

    No Known Activations