© 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. 2928
    Prev
    Next
    INDEX
    Explanations

    following "is" or "are"

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

    The neuron flags attention‐grabbing promotional or highlight phrases—words used to call out superlatives, favorites, and “must‐see” attractions (e.g. “best,” “favorite,” “main attraction,” “highlight,” “jewel in the crown”).

    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
     weitere
    0.80
     belangrijke
    0.74
     дальнейшем
    0.72
     ulteriori
    0.69
     számos
    0.68
    新たな
    0.68
     различни
    0.68
     menambah
    0.68
     σημαν
    0.66
     differenza
    0.66
    POSITIVE LOGITS
    的是
    1.19
     ialah
    1.16
     consists
    1.12
    是在
    1.11
     adalah
    1.10
    ಂದರೆ
    1.10
     consisted
    1.04
     عبارت
    1.02
    在于
    1.01
     হলো
    0.99
    Activations Density 0.594%

    No Known Activations