© 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. 34236
    Prev
    Next
    INDEX
    Explanations

    http error codes

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

    The neuron activates on standalone three‐digit numbers that correspond to HTTP status/error codes.

    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
     péro
    -1.73
     trám
    -1.70
     tragé
    -1.63
     lã
    -1.60
     estrelas
    -1.57
    婠
    -1.55
     farba
    -1.52
     wó
    -1.52
     bambou
    -1.50
    谞
    -1.50
    POSITIVE LOGITS
    X
    1.70
    P
    1.69
    U
    1.62
    B
    1.55
    C
    1.55
    N
    1.49
    G
    1.48
    T
    1.42
    2
    1.40
    M
    1.39
    Activations Density 0.005%

    No Known Activations