© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3145
    Prev
    Next
    INDEX
    Explanations

    know say

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

    The neuron spotlights filler and conversational discourse markers (e.g. “uh,” “you know”).

    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_24_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
     (
    0.52
    /
    0.50
     promptly
    0.46
     พร้อม
    0.45
     carelessly
    0.45
     loudly
    0.43
     abruptly
    0.41
    ゞ
    0.41
     esteemed
    0.41
     หลัง
    0.41
    POSITIVE LOGITS
     uh
    0.73
     äh
    0.71
     ähm
    0.69
     Uh
    0.65
     diciamo
    0.64
    uh
    0.63
     Ehm
    0.60
     ehm
    0.59
     Like
    0.59
    みたいな
    0.59
    Activations Density 0.004%

    No Known Activations