© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70765
    Prev
    Next
    INDEX
    Explanations

    python programming keywords

    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_22/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
     oeil
    -0.91
     refirió
    -0.89
    Atlético
    -0.84
     คน
    -0.81
     linge
    -0.79
     hlavní
    -0.79
    Пример
    -0.77
     alcool
    -0.77
    ORDAN
    -0.77
    éticos
    -0.75
    POSITIVE LOGITS
    cendo
    1.03
    Since
    0.96
    vaded
    0.94
     laws
    0.93
    This
    0.92
    ducers
    0.92
     system
    0.92
    pig
    0.85
    zość
    0.85
    When
    0.84
    Activations Density 0.415%

    No Known Activations