© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101338
    Prev
    Next
    INDEX
    Explanations

    query parameters

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

    question marks in URL query strings.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects the presence of URL query-string separators (e.g. “?” and “&”) in code or text.

    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
     even
    -2.39
     not
    -2.13
     незавер
    -2.00
     blatantly
    -1.99
     how
    -1.95
     unusually
    -1.94
     undeniably
    -1.93
     burgeoning
    -1.87
     those
    -1.87
     by
    -1.87
    POSITIVE LOGITS
    沨
    2.34
    ⩴
    2.20
    
    2.14
     และ
    1.98
     you
    1.93
     fazendo
    1.79
     Dinas
    1.79
     komplet
    1.79
    歟
    1.79
    を選ぶ
    1.78
    Activations Density 0.013%

    No Known Activations