© 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. 22-GEMMASCOPE-RES-131K
    7. 35528
    Prev
    Next
    INDEX
    Explanations

    web service endpoints http get

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

    This neuron detects HTTP “get” (and related GET-route) declarations in code or routing definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    It
    -1.08
    with
    -1.01
    BASE
    -1.00
     FÜR
    -0.98
     Verfü
    -0.98
     Jahrhundert
    -0.97
    ORDER
    -0.96
     global
    -0.92
    <b>
    -0.91
    System
    -0.90
    POSITIVE LOGITS
    Sola
    1.09
     །
    1.05
    MEMORANDUM
    1.03
    Tenor
    0.98
    ése
    0.96
    programma
    0.95
    eBook
    0.95
    Numerology
    0.95
    Slovakia
    0.94
    ┭
    0.94
    Activations Density 0.001%

    No Known Activations