© 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. 34-GEMMASCOPE-RES-131K
    7. 33125
    Prev
    Next
    INDEX
    Explanations

    document structure markers

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

    The neuron activates on document‐formatting divider lines or page markers (e.g. sequences of dashes or standalone page numbers).

    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
    radan
    -0.83
    できなかった
    -0.81
    häuse
    -0.80
    étique
    -0.78
    ﹋
    -0.77
    året
    -0.77
    しなかった
    -0.74
    瓴
    -0.73
    odetic
    -0.73
    Means
    -0.73
    POSITIVE LOGITS
     konusunda
    0.88
     Беларуси
    0.86
    manian
    0.79
     quintessential
    0.79
    országban
    0.78
     chữ
    0.78
     deth
    0.77
    ຮ
    0.77
    azine
    0.75
    佯
    0.75
    Activations Density 0.002%

    No Known Activations