© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33578
    Prev
    Next
    INDEX
    Explanations

    networking headers and parameters

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

    The neuron fires on code tokens that set up or reference HTTP request headers and related configuration objects.

    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
     disponibili
    -1.07
     such
    -1.04
     chrétien
    -1.00
     favoritas
    -0.96
    脱毛
    -0.96
    ников
    -0.95
    SequentialGroup
    -0.93
     neige
    -0.93
     bienvenue
    -0.92
     each
    -0.91
    POSITIVE LOGITS
    Both
    1.12
    vokat
    1.09
     reż
    1.05
    
    1.03
    ilité
    1.00
     démarche
    0.98
    kę
    0.97
    éget
    0.96
    Мой
    0.96
    both
    0.95
    Activations Density 0.002%

    No Known Activations