© 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. 10200
    Prev
    Next
    INDEX
    Explanations

    links, `/`, role, lists

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

    This neuron fires on numeric strings (especially multi‐digit numbers or decimal numbers) within URLs or URL‐like paths.

    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
     meskipun
    1.03
    ų
    0.93
     Ү
    0.88
    Ү
    0.87
    ﺭ
    0.87
    ený
    0.86
    дың
    0.85
    an
    0.84
    ੦
    0.83
    תו
    0.82
    POSITIVE LOGITS
     deep
    0.79
    }">${
    0.77
    elements
    0.76
     aisles
    0.73
     elements
    0.71
     choice
    0.70
    Dieses
    0.70
     praise
    0.69
     corsi
    0.69
     distractions
    0.68
    Activations Density 0.001%

    No Known Activations