© 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. 9290
    Prev
    Next
    INDEX
    Explanations

    open mouth wide

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

    The neuron strongly activates on the standalone word “Open,” as used to begin an instruction or section heading.

    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
     Lý
    0.63
     setCurrent
    0.55
     Lexington
    0.54
     ಇ
    0.54
     Updated
    0.53
     TABLES
    0.53
    نيه
    0.53
     territoriale
    0.53
     Linie
    0.53
     quadrilateral
    0.52
    POSITIVE LOGITS
    apt
    0.63
    dressed
    0.61
    apture
    0.61
    িয়ান
    0.59
    oader
    0.58
     dressed
    0.57
    显得
    0.56
    coherent
    0.55
    勻
    0.55
    表現
    0.54
    Activations Density 0.000%

    No Known Activations