© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99891
    Prev
    Next
    INDEX
    Explanations

    related literature citations

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

    The neuron is detecting section‐divider lines made up of repeated equals signs (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_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
    onomie
    -0.73
     приходится
    -0.70
     请求
    -0.69
     annulus
    -0.69
    BOTTOM
    -0.69
    ionine
    -0.67
    過程中
    -0.66
     bbox
    -0.65
    atas
    -0.65
     学生
    -0.64
    POSITIVE LOGITS
     Bal
    0.77
    IOUtils
    0.75
     Raj
    0.68
     ry
    0.68
    öld
    0.66
    Bal
    0.65
    InfoList
    0.65
    쏟
    0.64
     type
    0.63
    нены
    0.63
    Activations Density 0.122%

    No Known Activations