© 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. 6768
    Prev
    Next
    INDEX
    Explanations

    Happiness and amusement

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

    The neuron strongly activates on isolated numeric or enumeration‐style tokens (e.g. page or section numbers, list/item markers, and similar standalone codes).

    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
     taxation
    0.82
    િ
    0.79
     taxa
    0.79
     opponents
    0.77
    р
    0.77
     conquests
    0.75
     outp
    0.75
    ড়ি
    0.74
    डी
    0.74
     normalcy
    0.73
    POSITIVE LOGITS
     함께
    0.74
     Selle
    0.71
     Еще
    0.68
     быстро
    0.68
     Ну
    0.66
     Slam
    0.66
    ván
    0.66
     Sena
    0.66
     Щ
    0.65
     Teflon
    0.65
    Activations Density 0.000%

    No Known Activations