© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11503
    Prev
    Next
    INDEX
    Explanations

    `randint` or `sampler`

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

    The neuron fires on tokens that are numeric or contain digits (e.g. years, measurement values, counts, citation 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_31_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
    ㇁
    0.64
    CLR
    0.60
     uninterrupted
    0.57
     Chichester
    0.57
     ा
    0.56
     Terbaru
    0.54
     GENER
    0.54
     Jackman
    0.53
    Gamb
    0.52
     와
    0.52
    POSITIVE LOGITS
    requ
    0.64
     conductor
    0.59
    ണി
    0.59
    ändig
    0.59
     পাঠানোর
    0.58
     هنت
    0.57
     جانتے
    0.56
    オク
    0.55
    呀
    0.55
    硫
    0.55
    Activations Density 0.052%

    No Known Activations