© 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. 10250
    Prev
    Next
    INDEX
    Explanations

    code snippet endings

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

    The neuron responds to very high‐frequency, broadly common tokens (i.e. ubiquitous words that recur across many different contexts).

    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
    م
    0.88
    ميل
    0.81
    ך
    0.79
    ع
    0.76
    تان
    0.73
    مول
    0.72
    ין
    0.71
    ی
    0.71
    ب
    0.71
    ات
    0.68
    POSITIVE LOGITS
     ต้น
    0.84
     территория
    0.84
     itulah
    0.82
     источники
    0.79
     이라고
    0.78
     дверь
    0.76
     ယ
    0.76
     кноп
    0.75
    입
    0.75
     Люди
    0.75
    Activations Density 0.000%

    No Known Activations