© 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. 8415
    Prev
    Next
    INDEX
    Explanations

    vitamins, fairytales, claims

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

    The neuron strongly activates on the first (or key) word of multi‐word proper names—e.g. product, organization, test, or book titles.

    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
    (),
    0.58
    （
    0.56
    ():
    0.55
    ：
    0.53
    ของ
    0.49
    是
    0.49
    listOf
    0.48
    photo
    0.48
    info
    0.48
    は
    0.48
    POSITIVE LOGITS
     ragazzi
    0.53
     perplexed
    0.53
     zákon
    0.52
     dalamnya
    0.52
     oči
    0.51
     drenched
    0.50
     jongens
    0.50
     comandante
    0.50
     República
    0.50
     Cumhur
    0.50
    Activations Density 0.287%

    No Known Activations