© 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. 7688
    Prev
    Next
    INDEX
    Explanations

    seek out

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

    The neuron fires most strongly on second‐person imperative or call-to-action verbs (e.g. “check,” “try,” “get,” “find,” “figure out”).

    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
    Up
    0.91
     Up
    0.90
    up
    0.64
     업
    0.63
    アップ
    0.60
    Ups
    0.60
    BtnUp
    0.59
     UP
    0.59
    upa
    0.58
     アップ
    0.57
    POSITIVE LOGITS
     out
    4.03
    out
    2.95
    出
    2.89
    出的
    2.77
    出一
    2.45
    出一个
    2.44
    出了
    2.42
     Out
    2.39
    出來
    2.38
    Out
    2.34
    Activations Density 0.554%

    No Known Activations