© 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. 8361
    Prev
    Next
    INDEX
    Explanations

    faster, database, generation, made

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

    The neuron fires on floating‐point number tokens (numbers with decimal points).

    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
     آس
    0.82
     uncover
    0.75
     perceive
    0.72
    ﺔ
    0.71
     tzv
    0.70
     unsatisfactory
    0.70
     ghost
    0.69
     gag
    0.69
     Ekim
    0.68
     खोजने
    0.68
    POSITIVE LOGITS
    ngth
    0.82
    costs
    0.80
    ZX
    0.79
    Build
    0.79
    وتی
    0.78
    COP
    0.77
    ज
    0.76
    npmjs
    0.75
    ти
    0.74
    বিদ
    0.73
    Activations Density 0.000%

    No Known Activations