© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9664
    Prev
    Next
    INDEX
    Explanations

    error messages module not found

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

    The neuron fires on numeric tokens—especially decimals or measurements—so it’s detecting numbers (often with units or in stats/technical contexts).

    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
    kę
    0.92
    बाट
    0.84
     серпня
    0.78
    ة
    0.78
     byť
    0.77
    ція
    0.77
     reiterate
    0.77
     движения
    0.76
    ູບ
    0.76
    ان
    0.75
    POSITIVE LOGITS
    J
    0.74
    DN
    0.72
    liste
    0.69
    ../../../
    0.69
    tarif
    0.69
    K
    0.65
     {.
    0.64
    慘
    0.64
    Lot
    0.63
    Z
    0.63
    Activations Density 0.000%

    No Known Activations