© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6263
    Prev
    Next
    INDEX
    Explanations

    next occurrence, net, blood

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

    The neuron strongly activates on numeric tokens—particularly multi‐digit numbers and decimal values—flagging any kind of numerical data 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
    wpi
    0.85
    umenical
    0.80
    cellaneous
    0.79
    imiya
    0.79
    d
    0.79
    adığı
    0.77
    inuous
    0.77
     ܘ
    0.76
    revolution
    0.76
    lr
    0.75
    POSITIVE LOGITS
    箇所
    0.71
     effetti
    0.71
    DEFINE
    0.71
     lagen
    0.70
     ocurre
    0.68
     spéc
    0.68
     punto
    0.67
     salivary
    0.67
     vous
    0.66
     altri
    0.65
    Activations Density 0.000%

    No Known Activations