© 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. 16152
    Prev
    Next
    INDEX
    Explanations

    code loops and syntax

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

    The neuron is detecting very common, high‐frequency tokens (e.g. short function words, pronouns, and everyday verbs).

    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
    fur
    0.80
    fas
    0.78
    ekar
    0.75
    s
    0.75
    fv
    0.73
    가
    0.73
    Minimized
    0.71
    fu
    0.69
    fli
    0.69
     אי
    0.68
    POSITIVE LOGITS
    〉
    0.77
    يون
    0.72
     Officials
    0.72
     milliards
    0.71
    ய்ட
    0.70
    шон
    0.66
     концерт
    0.66
    neſs
    0.66
    ద్ద
    0.66
     букмекеры
    0.66
    Activations Density 0.001%

    No Known Activations