© 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. 11431
    Prev
    Next
    INDEX
    Explanations

    Increment the index

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

    The neuron selectively fires on key content nouns and topic‐specific terms (e.g. “heart,” “implants,” “shades,” “others”) rather than on function words.

    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
    кат
    0.86
    ол
    0.79
    ні
    0.77
    ложен
    0.75
    казыва
    0.72
    ేవ
    0.72
    겔
    0.70
    қа
    0.70
    менно
    0.70
     roused
    0.68
    POSITIVE LOGITS
     เดี๋ยว
    0.80
     liquidity
    0.75
    。“
    0.75
    ্ড
    0.75
     hairstyle
    0.75
    我覺得
    0.74
    Measure
    0.73
     neckline
    0.72
    bildung
    0.71
    ಪ
    0.70
    Activations Density 0.000%

    No Known Activations