© 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. 33066
    Prev
    Next
    INDEX
    Explanations

    markdown table delimiters

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

    The neuron activates on ASCII‐style table border and column‐separator characters (e.g. “|”, “+”, “—”).

    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
     ہی
    -0.85
    Moda
    -0.80
     still
    -0.78
     золото
    -0.76
    razza
    -0.76
    pahan
    -0.75
     染
    -0.74
     even
    -0.74
     мон
    -0.74
     Gelen
    -0.73
    POSITIVE LOGITS
     zuneh
    0.84
    another
    0.81
    below
    0.79
     Bearbeit
    0.78
    Unmount
    0.77
    require
    0.77
     חשוב
    0.76
    UCKY
    0.75
     mỗi
    0.74
     Bihar
    0.73
    Activations Density 0.151%

    No Known Activations