© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2848
    Prev
    Next
    INDEX
    Explanations

    website suffixes followed by slash

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

    The neuron specifically detects top‐level domain tokens (like “.com,” “.org,” “.edu,” “.gov”) in URLs.

    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
     Ε
    0.77
     Ա
    0.73
     Tecnología
    0.71
     これらの
    0.69
     この
    0.69
     Wür
    0.69
     Aéroport
    0.68
     Β
    0.68
     atthe
    0.68
     Université
    0.67
    POSITIVE LOGITS
    shopping
    0.73
    signup
    0.70
    not
    0.67
    ot
    0.66
    washington
    0.66
    request
    0.65
    xpath
    0.65
    sr
    0.65
    msg
    0.64
    blog
    0.64
    Activations Density 0.000%

    No Known Activations