© 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. 11249
    Prev
    Next
    INDEX
    Explanations

    creation / layout / connection

    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
    s
    1.03
     J
    0.78
     ಹ
    0.72
     M
    0.71
    lif
    0.71
    v
    0.68
    level
    0.68
     H
    0.67
     TA
    0.67
    sala
    0.67
    POSITIVE LOGITS
    ้
    0.89
     όχι
    0.88
     söyled
    0.86
    ью
    0.84
    ចេញ
    0.83
     يكن
    0.83
    ფორმა
    0.83
    İŞ
    0.83
    Ϥ
    0.83
    цы
    0.82
    Activations Density 0.000%

    No Known Activations