© 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. 34-GEMMASCOPE-RES-131K
    7. 31826
    Prev
    Next
    INDEX
    Explanations

    Party name / About / Our Difference

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

    The neuron fires strongly on snippets that set or inspect HTTP “Access-Control-” response headers (i.e. CORS header handling).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    iuo
    -0.75
     Mindy
    -0.74
    Toad
    -0.72
     моги
    -0.72
     pitches
    -0.71
    covid
    -0.71
    امت
    -0.70
     Syrie
    -0.69
     chute
    -0.69
     intruders
    -0.69
    POSITIVE LOGITS
    暴露
    0.94
     iconLine
    0.84
    stawa
    0.79
    Activités
    0.79
     legge
    0.78
     Samp
    0.78
    ologue
    0.77
    brave
    0.76
     samh
    0.76
     мг
    0.75
    Activations Density 0.002%

    No Known Activations