© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8700
    Prev
    Next
    INDEX
    Explanations

    millinery endeavor

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

    This neuron detects uppercase acronyms or initialisms (all-caps abbreviations).

    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
     отлича
    0.65
     ginh
    0.61
     intravenous
    0.58
    deltaTime
    0.58
     diffus
    0.58
     dulce
    0.57
     проходить
    0.57
    햐
    0.56
     nanofibers
    0.54
     arterioles
    0.54
    POSITIVE LOGITS
    US
    0.66
     สาว
    0.63
    ATOR
    0.63
    ®.
    0.59
    ®,
    0.58
     男
    0.57
    ฯ
    0.57
    ING
    0.56
     製品
    0.56
     ノー
    0.56
    Activations Density 0.001%

    No Known Activations