© 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. 128983
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on code or markup indicating a redirect or refresh (e.g. “redirect,” HTML `<meta refresh>`, response‐redirect calls, and related tags).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    redirect with notice

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     olev
    -0.94
    TableName
    -0.90
     traditionelle
    -0.90
     ennen
    -0.88
    ➛
    -0.87
    oulders
    -0.87
     kommende
    -0.86
    >=</
    -0.85
    rrbracket
    -0.85
    _))
    -0.85
    POSITIVE LOGITS
    続ける
    0.99
    初め
    0.96
    udahkan
    0.88
    zość
    0.85
    決め
    0.85
    íble
    0.85
     budowy
    0.84
    گروه
    0.84
     plentiful
    0.84
    vaart
    0.84
    Activations Density 0.003%

    No Known Activations