© 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. 10-GEMMASCOPE-RES-131K
    7. 102695
    Prev
    Next
    INDEX
    Explanations

    LaTeX math and code delimiters

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

    line breaks in mathematical notation or code, particularly in LaTeX matrices and piecewise functions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     by
    -1.81
     tanam
    -1.77
     bekasi
    -1.59
     kirim
    -1.59
     has
    -1.59
    簡單
    -1.56
    出来ました
    -1.56
    してました
    -1.55
    Transkrypt
    -1.55
     will
    -1.55
    POSITIVE LOGITS
    ⬈
    1.71
    o
    1.58
    </h3>
    1.49
    也不能
    1.47
    ‖
    1.45
    </em>
    1.45
     It
    1.44
    你也
    1.42
     sua
    1.41
    都不能
    1.40
    Activations Density 0.005%

    No Known Activations