© 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. 10974
    Prev
    Next
    INDEX
    Explanations

    blushed or shook or nodded

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

    This neuron fires on personal names in the narrative, especially Chinese‐style character names.

    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
    へと
    0.75
    霎
    0.71
    了起来
    0.68
     detonations
    0.66
    顿时
    0.64
    を開始
    0.63
    ያንዳ
    0.61
    震撼
    0.61
    歓
    0.60
     begun
    0.59
    POSITIVE LOGITS
     investi
    0.64
     altid
    0.61
     Nge
    0.60
     الآخر
    0.59
    zcan
    0.57
    犟
    0.57
     uncomplicated
    0.56
     குழந்தையின்
    0.56
     affectionate
    0.56
     sometimes
    0.55
    Activations Density 0.010%

    No Known Activations