© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12040
    Prev
    Next
    INDEX
    Explanations

    why exists

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

    The neuron activates on numeric tokens that are floating‐point numbers (i.e. contain digits plus a decimal point).

    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
    に含ま
    0.70
    щ
    0.70
    ntz
    0.68
     пона
    0.65
    k
    0.65
     суток
    0.64
    by
    0.63
    ре
    0.63
    s
    0.63
    пс
    0.62
    POSITIVE LOGITS
     oito
    0.86
     atth
    0.86
     Airtel
    0.84
     Desember
    0.82
     veinte
    0.81
    বীর
    0.80
    人は
    0.80
     पाँच
    0.80
     อย่า
    0.80
     karne
    0.80
    Activations Density 0.001%

    No Known Activations