© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8224
    Prev
    Next
    INDEX
    Explanations

    dear val

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

    This neuron flags highly technical, formal writing—especially patent-style or scientific passages with specific terms (e.g. “upper/lower pattern,” “scanning electron microscopic image”) and numerical references.

    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
     flavonoid
    0.77
    📑
    0.72
    䥑
    0.70
     Moris
    0.69
    
    0.69
     daug
    0.68
    <unused2197>
    0.68
    pieceSelection
    0.68
    spacePad
    0.68
    presas
    0.68
    POSITIVE LOGITS
    ně
    0.57
    а
    0.55
    أ
    0.54
    isset
    0.52
    ando
    0.52
    acle
    0.52
    ā
    0.52
     Duterte
    0.50
     ₹
    0.50
     etcétera
    0.50
    Activations Density 1.640%

    No Known Activations