© 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. 15660
    Prev
    Next
    INDEX
    Explanations

    news sources websites organizations

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

    The neuron detects URLs (web addresses) in the text.

    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
    www
    0.40
     Einkauf
    0.40
     Universität
    0.39
     Developments
    0.36
    HTTPS
    0.35
     Você
    0.34
     الإنترنت
    0.33
    🆈
    0.33
     Updates
    0.33
     bisschen
    0.33
    POSITIVE LOGITS
     penultimate
    0.32
     complacency
    0.32
     urgency
    0.31
     karş
    0.31
     subpar
    0.30
     pivots
    0.30
    polarity
    0.30
     faulted
    0.30
     longitud
    0.29
     polarity
    0.29
    Activations Density 0.023%

    No Known Activations