© 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. 9625
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other numbers

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

    The neuron fires on numeric tokens, especially multi‐digit numbers or numerical sequences.

    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
    шенный
    0.64
    ере
    0.61
    ﾛ
    0.60
     esophagus
    0.56
     ท
    0.55
     आपले
    0.54
     deems
    0.54
    ره
    0.53
    ремен
    0.53
     membrana
    0.53
    POSITIVE LOGITS
    羌
    0.59
     பார்த்து
    0.59
     mistress
    0.57
     convirt
    0.56
     HOUR
    0.55
     aceptar
    0.54
     മാന
    0.54
     uni
    0.54
    ード
    0.54
     सप्ताह
    0.53
    Activations Density 0.092%

    No Known Activations