© 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. 3917
    Prev
    Next
    INDEX
    Explanations

    modelBengali or common words

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

    The neuron strongly activates on numeric tokens containing decimal points (i.e. 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
    各个
    0.66
     dichas
    0.62
    <unused2127>
    0.60
    <unused2117>
    0.59
     các
    0.58
     operatives
    0.57
     पक्षा
    0.57
    ς
    0.57
    <unused2157>
    0.56
     slov
    0.55
    POSITIVE LOGITS
    Actually
    0.82
    That
    0.80
    我
    0.80
    Seems
    0.78
    You
    0.76
    Honestly
    0.74
    Doesn
    0.73
     मुझे
    0.73
    Sorry
    0.73
    Really
    0.72
    Activations Density 0.001%

    No Known Activations