© 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. 5886
    Prev
    Next
    INDEX
    Explanations

    pause, halt, or end actions

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

    This neuron fires strongly on very common high‐frequency English function words (e.g. “the,” “is,” “to,” “you”).

    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
     nabí
    0.77
     odborn
    0.71
     offerings
    0.71
    ‌پ
    0.70
     предлагает
    0.70
     определяет
    0.70
     увели
    0.69
     uj
    0.68
     ниже
    0.68
     المدير
    0.68
    POSITIVE LOGITS
    Painting
    0.84
    arantine
    0.79
    い
    0.78
    ă
    0.77
    ocrine
    0.77
    闿
    0.77
    Nurse
    0.75
    র্দ
    0.74
    丧
    0.73
    게
    0.73
    Activations Density 0.000%

    No Known Activations