© 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. 13816
    Prev
    Next
    INDEX
    Explanations

    Stable Diffusion

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

    The neuron activates on numeric tokens containing decimal points (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
     insensitive
    0.73
    łeś
    0.72
    字符
    0.69
     ছেলেরা
    0.69
     nasal
    0.69
    聲
    0.68
     UNDER
    0.68
     socios
    0.68
     WOMEN
    0.67
     SOCIETY
    0.66
    POSITIVE LOGITS
    
    0.88
    )’
    0.80
    Æ
    0.80
    AGO
    0.79
    rament
    0.79
    ades
    0.78
    بس
    0.78
    abul
    0.75
    кмекер
    0.72
    ichar
    0.72
    Activations Density 0.000%

    No Known Activations