© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127328
    Prev
    Next
    INDEX
    Explanations

    web links

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

    The neuron activates on URL scheme tokens (e.g. “http://” or “https://”), effectively detecting the start of web addresses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    などを
    -1.66
    などは
    -1.62
    などが
    -1.62
    ppé
    -1.57
    着脸
    -1.56
     bisschen
    -1.55
     другая
    -1.54
    izacja
    -1.53
     peluche
    -1.52
    なども
    -1.52
    POSITIVE LOGITS
     it
    2.56
     the
    1.88
     each
    1.79
     every
    1.68
    LikeLiked
    1.55
     setiap
    1.53
     these
    1.52
    ཋ
    1.51
    ❔
    1.48
     they
    1.46
    Activations Density 0.017%

    No Known Activations