© 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. 12009
    Prev
    Next
    INDEX
    Explanations

    Q: programming or technical queries

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

    XML documentation comment tags closing the `<summary>` section in code.

    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
    icona
    -1.98
     Gemeinsame
    -1.86
     then
    -1.85
     if
    -1.77
    沺
    -1.77
     společnost
    -1.73
    apnews
    -1.71
    釭
    -1.71
     của
    -1.67
     Kondisi
    -1.66
    POSITIVE LOGITS
    In
    2.03
    in
    1.84
     “
    1.83
     milieux
    1.80
     ”
    1.80
    The
    1.79
    on
    1.65
    镲
    1.64
     reporte
    1.60
    ↵↵
    1.58
    Activations Density 0.002%

    No Known Activations