© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79209
    Prev
    Next
    INDEX
    Explanations

    HTTP status code errors

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

    This neuron fires on numeric HTTP status codes (and the associated “error” context) appearing in the text.

    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
    おそ
    -0.99
     egip
    -0.89
    لاع
    -0.88
    Jump
    -0.83
    わから
    -0.81
    March
    -0.80
    تصویر
    -0.80
     Überg
    -0.79
     awesome
    -0.78
    ⊿
    -0.78
    POSITIVE LOGITS
    クタイ
    0.87
    minente
    0.84
    쁨
    0.82
     några
    0.82
     NLRB
    0.81
    charest
    0.80
     objection
    0.79
    љ
    0.79
     другим
    0.79
    Tacos
    0.79
    Activations Density 0.013%

    No Known Activations