© 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. 4326
    Prev
    Next
    INDEX
    Explanations

    `f" print`

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

    The neuron strongly activates on numeric measurements—especially floating‐point values (e.g. concentrations, percentages, hazard ratios, p‐values) 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
    Eas
    0.89
    ✐
    0.85
    ль
    0.80
    IES
    0.77
    imps
    0.77
    Examples
    0.76
    ⁈
    0.74
    inverted
    0.70
    薔
    0.67
    ㎡
    0.65
    POSITIVE LOGITS
     longtime
    0.87
     adunay
    0.87
     joue
    0.86
     واذا
    0.85
     connaissez
    0.80
    ୍ୟ
    0.79
    "${
    0.78
     sorprend
    0.77
     ancak
    0.77
     verein
    0.76
    Activations Density 0.000%

    No Known Activations