© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9629
    Prev
    Next
    INDEX
    Explanations

    asking if others experience

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

    This neuron responds to occurrences of the word “anyone” (especially in question phrases like “Has anyone…” or “Anyone …?”)

    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
     тобой
    0.67
     станов
    0.64
    ięcy
    0.64
     중요하다
    0.59
    Ꭸ
    0.58
     とする
    0.57
     ramus
    0.57
     pravil
    0.56
     значит
    0.55
    Ꮰ
    0.55
    POSITIVE LOGITS
     Had
    0.66
    或者
    0.63
     veya
    0.60
    模拟
    0.60
     had
    0.58
    experienced
    0.58
    experience
    0.57
     경험
    0.57
    had
    0.57
    预测
    0.57
    Activations Density 0.015%

    No Known Activations