© 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. 6686
    Prev
    Next
    INDEX
    Explanations

    programming syntax, types, and code

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

    The neuron fires most strongly on numeric page‐view or visitor count values (e.g. the numbers following “has viewed by”).

    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
    很
    0.85
    t
    0.84
    （
    0.81
    ifères
    0.73
    n
    0.70
    ز
    0.69
    有个
    0.68
    ،
    0.68
    印
    0.68
    linux
    0.67
    POSITIVE LOGITS
     substituents
    0.96
     Noether
    0.90
     sexes
    0.88
     momenta
    0.86
     meiosis
    0.84
     hips
    0.84
     Pasadena
    0.84
     covalent
    0.83
     trivalent
    0.82
     hapl
    0.81
    Activations Density 0.001%

    No Known Activations