© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    "called" or "termed" followed by a name

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

    The neuron detects numeric tokens containing decimal points (floating‐point 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
     прямо
    0.63
    gcd
    0.62
    んですね
    0.59
    Meier
    0.59
    ühlt
    0.58
    ()->
    0.56
    GCD
    0.56
    unordered
    0.55
     codimension
    0.55
     constat
    0.55
    POSITIVE LOGITS
     “[
    0.63
     Courage
    0.63
     “
    0.62
     “(
    0.61
     Thursday
    0.59
     “…
    0.59
     Hvis
    0.59
     pilgrimage
    0.57
    mesi
    0.57
    ंमध्ये
    0.57
    Activations Density 0.045%

    No Known Activations