© 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. 13206
    Prev
    Next
    INDEX
    Explanations

    subroutine, png, singular, open

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

    The neuron selectively activates on tokens that are purely or predominantly numeric (i.e. number strings or codes).

    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
     ۷
    0.60
    ７
    0.57
     S
    0.56
     D
    0.56
     K
    0.55
     quadru
    0.52
    7
    0.52
     R
    0.52
    ６
    0.51
     lipids
    0.51
    POSITIVE LOGITS
     hoặc
    1.00
     또는
    0.89
     veya
    0.87
     หรือ
    0.85
     или
    0.82
     või
    0.80
     অথবা
    0.80
     અથવા
    0.80
     tại
    0.80
     किंवा
    0.79
    Activations Density 0.116%

    No Known Activations