© 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. 22-GEMMASCOPE-RES-131K
    7. 67865
    Prev
    Next
    INDEX
    Explanations

    web request/response handling

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

    This neuron fires on references to the `response` object (and its property accesses like `response.status`, `response.url`, etc.)

    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
     on
    -1.54
     just
    -1.31
     their
    -1.31
     less
    -1.30
     even
    -1.27
     at
    -1.27
     in
    -1.21
     system
    -1.21
     still
    -1.20
    ışı
    -1.20
    POSITIVE LOGITS
    那时候
    1.63
    both
    1.59
     afore
    1.58
    整天
    1.53
     nabíz
    1.52
    ⎆
    1.39
    也不會
    1.38
    Джере
    1.38
    ඍ
    1.37
     Hinsicht
    1.36
    Activations Density 0.013%

    No Known Activations