© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9499
    Prev
    Next
    INDEX
    Explanations

    ranging from

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

    The neuron flags numeric measurement tokens—especially multi‐digit or decimal values denoting capacities, ranges, or other quantitative statistics.

    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
     बातचीत
    0.73
    たない
    0.62
    CROSS
    0.59
    炮
    0.58
     दुसऱ्या
    0.57
    ému
    0.55
    后的
    0.54
    ECS
    0.54
    /:
    0.53
    上述
    0.53
    POSITIVE LOGITS
     ranging
    1.20
    ranging
    1.09
     Ranges
    0.93
     ranges
    0.91
     ranged
    0.91
     диапазо
    0.91
     rango
    0.88
     range
    0.81
     Range
    0.81
     диапа
    0.81
    Activations Density 0.219%

    No Known Activations