© 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. 10567
    Prev
    Next
    INDEX
    Explanations

    start with

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

    The neuron responds to 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
     encontrada
    0.83
    ссий
    0.82
    рафон
    0.82
    に近い
    0.79
    ಿಯಾ
    0.78
    찔
    0.77
    OSED
    0.76
     unscathed
    0.75
     apreciar
    0.73
    𝙄
    0.73
    POSITIVE LOGITS
    n
    1.02
    nob
    0.73
    很多
    0.73
    湳
    0.70
    डी
    0.69
    因為
    0.69
    てる
    0.69
    nout
    0.69
    nv
    0.68
    Butler
    0.67
    Activations Density 0.000%

    No Known Activations