© 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. 22-GEMMASCOPE-RES-131K
    7. 27415
    Prev
    Next
    INDEX
    Explanations

    retrieves, description, test, reducing

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

    The neuron fires strongly on words that appear at the beginnings of lines or sections.

    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
    Ahol
    -0.94
    ウール
    -0.92
     every
    -0.91
    过来了
    -0.90
    Cela
    -0.90
     soldats
    -0.90
     Enfer
    -0.89
    åringen
    -0.88
     แต่ง
    -0.88
    Usuarios
    -0.87
    POSITIVE LOGITS
     to
    1.30
    所示
    0.96
    ᵖ
    0.95
    cookieParser
    0.93
    》，
    0.93
    UnitTesting
    0.91
     翔
    0.91
     is
    0.90
     zwłaszcza
    0.89
    ลิ
    0.89
    Activations Density 0.001%

    No Known Activations