© 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. 102605
    Prev
    Next
    INDEX
    Explanations

    technical document formatting

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

    closing delimiters in structured technical or mathematical text, particularly for environments like equations, alignments, and code blocks.

    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
     of
    -2.50
     consequently
    -2.09
     to
    -1.91
     subsequently
    -1.82
     with
    -1.82
    ⍽
    -1.76
     Whether
    -1.76
     Bahkan
    -1.75
     prominently
    -1.69
     then
    -1.67
    POSITIVE LOGITS
     ещё
    2.16
    ↵↵
    2.14
     prouver
    1.94
    rägen
    1.91
    seers
    1.89
    ์
    1.89
    撺
    1.86
     provoquer
    1.85
     estekak
    1.82
     compradores
    1.73
    Activations Density 0.001%

    No Known Activations