© 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. 4312
    Prev
    Next
    INDEX
    Explanations

    <end_of_turn>

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

    The neuron highlights unusually salient or content‐bearing tokens—rare or informative words (e.g. “well,” “such,” “isn’t,” numeric citations) that stand out in the document rather than common 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
    ian
    0.58
    y
    0.53
    alé
    0.50
    ol
    0.50
    ot
    0.50
    olak
    0.49
    gy
    0.49
    o
    0.49
    .
    0.48
    dan
    0.48
    POSITIVE LOGITS
     isang
    0.64
     一个
    0.63
     ধরিয়
    0.63
     một
    0.61
    Een
    0.61
    一個
    0.60
     jeśli
    0.59
     یک
    0.58
     Een
    0.58
     例文帳に追加
    0.57
    Activations Density 0.006%

    No Known Activations