© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9364
    Prev
    Next
    INDEX
    Explanations

    explaining or not explaining

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

    The neuron strongly activates on the common function words (especially personal pronouns like “you,” “I,” and auxiliaries such as “do,” “is,” “think,” “have”) occurring in direct‐speech or question/answer dialogue.

    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_31_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
     yc
    0.59
     १६
    0.56
    ☟
    0.56
     adalah
    0.55
     ১৬
    0.54
    stm
    0.53
    yc
    0.53
    不能为空
    0.53
    বার্ট
    0.53
     dovet
    0.53
    POSITIVE LOGITS
     Less
    0.56
     이에
    0.56
    睬
    0.55
     Klin
    0.54
     никакой
    0.54
     Petersburg
    0.53
     замет
    0.52
     Bush
    0.52
     النها
    0.52
     Examinations
    0.52
    Activations Density 0.077%

    No Known Activations