© 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. 11426
    Prev
    Next
    INDEX
    Explanations

    innate/adaptive immunity

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

    This neuron strongly activates on numeric tokens (e.g. list item numbers, dates, phone‐number digits)—in other words, it detects 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_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
    」、
    0.66
    vip
    0.65
    ”，
    0.64
    và
    0.64
    <u>
    0.63
    <code>
    0.62
    ，《
    0.61
    盡
    0.61
    }.\
    0.61
    both
    0.59
    POSITIVE LOGITS
     
    1.00
     Have
    0.99
     That
    0.91
     This
    0.90
     You
    0.90
     The
    0.88
     We
    0.86
     Fantasy
    0.84
     
    0.83
     There
    0.81
    Activations Density 0.302%

    No Known Activations