© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 16147
    Prev
    Next
    INDEX
    Explanations

    The neuron is a general “content‐word” detector—it lights up on semantically rich words (especially nouns and key topic terms) rather than on function words.

    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
    a
    0.84
    ittet
    0.72
    특별시
    0.70
    ی
    0.68
    %
    0.68
    های
    0.67
    ки
    0.66
    errorMessage
    0.66
     profitieren
    0.66
    ④
    0.66
    POSITIVE LOGITS
     suku
    0.84
     Після
    0.84
    Ві
    0.79
    Під
    0.76
    डिंग
    0.74
     букмекерлик
    0.74
     sawa
    0.74
     হয়নি
    0.74
    郸
    0.74
    闾
    0.73
    Activations Density 0.001%

    No Known Activations