© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1118
    Prev
    Next
    INDEX
    Explanations

    code boot and test paths

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

    file paths in source code, particularly those containing "src" followed by a forward slash.

    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
     on
    -2.39
     in
    -2.09
     to
    -1.98
     for
    -1.95
     not
    -1.73
     as
    -1.65
     an
    -1.64
     a
    -1.63
     within
    -1.59
     with
    -1.55
    POSITIVE LOGITS
     kampen
    1.66
     två
    1.52
     ideen
    1.46
    новение
    1.45
    :……
    1.44
     ferien
    1.43
     robuste
    1.42
     manuelle
    1.42
     faciliter
    1.41
     kalender
    1.40
    Activations Density 0.035%

    No Known Activations