© 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. 818
    Prev
    Next
    INDEX
    Explanations

    glowing, pulsating, dazzling, magnificent

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

    The neuron is keyed to narration or dialogue attribution cues—i.e. words and phrases that signal a speaker or the act of “saying” (e.g. instructor, said, asked, words, telling).

    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
     eventuali
    0.61
     możemy
    0.59
    นิยม
    0.58
     stycz
    0.57
    偲
    0.57
    references
    0.57
     referencing
    0.57
     eventual
    0.56
    لز
    0.56
     qualunque
    0.56
    POSITIVE LOGITS
     incompar
    0.86
     roared
    0.81
     undulating
    0.79
    只见
    0.79
     faintly
    0.77
    众人
    0.77
     屋
    0.76
     densely
    0.75
    不断
    0.72
     majestic
    0.72
    Activations Density 0.073%

    No Known Activations