© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4690
    Prev
    Next
    INDEX
    Explanations

    incoming HTTP requests

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

    The neuron fires strongly on numeric tokens—especially floating‐point numbers—flagging decimal figures 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
    de
    0.92
    t
    0.84
    te
    0.79
    시오
    0.77
    to
    0.76
    y
    0.74
    нить
    0.72
    bw
    0.72
    ta
    0.71
     şekilde
    0.70
    POSITIVE LOGITS
    Ⲑ
    0.83
    ИН
    0.82
    alaikums
    0.80
     Są
    0.79
    ozygous
    0.79
     riman
    0.79
     Ин
    0.77
     consulte
    0.77
    beitet
    0.76
     Интер
    0.76
    Activations Density 0.000%

    No Known Activations