© 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. 34-GEMMASCOPE-RES-131K
    4. 49889
    Prev
    Next
    INDEX
    Explanations

    keywords and their common contexts

    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_34/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
     ordinario
    -0.86
    Zdrav
    -0.85
     unlimited
    -0.84
     onCancelled
    -0.82
     civiliz
    -0.82
    CIUDAD
    -0.82
    Instrucciones
    -0.81
    papar
    -0.79
    ExternalTask
    -0.77
    resep
    -0.75
    POSITIVE LOGITS
     roulette
    1.09
     dump
    0.98
    incón
    0.93
    üd
    0.92
    ֵל
    0.92
    ๙
    0.91
     importancia
    0.90
    ыр
    0.89
     Roulette
    0.87
     vond
    0.87
    Activations Density 0.076%

    No Known Activations