© 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. 119939
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    还有
    -2.34
     wiederhol
    -2.20
     verbess
    -2.08
     auß
    -2.08
     zahlreichen
    -2.06
     klassischen
    -2.06
     erweiter
    -1.99
     erweiterten
    -1.98
     gleichzeitig
    -1.92
     wichtigen
    -1.89
    POSITIVE LOGITS
     such
    2.16
     and
    1.99
     Septembre
    1.73
     Januari
    1.72
     februari
    1.70
     Octobre
    1.70
     tabel
    1.68
     middel
    1.65
     Februari
    1.65
     própri
    1.65
    Activations Density 0.002%

    No Known Activations