© 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. 10-GEMMASCOPE-RES-131K
    7. 110620
    Prev
    Next
    INDEX
    Explanations

    universal acceptance health

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

    The word "universal" in various contexts, particularly in technical and healthcare documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ſſi
    -3.36
    댔
    -3.11
    
    -3.09
    腘
    -3.08
    mbgg
    -3.08
    筇
    -2.98
    𓁹
    -2.92
     they
    -2.89
    棡
    -2.84
     terrific
    -2.83
    POSITIVE LOGITS
    Just
    3.75
    While
    3.63
    After
    3.55
     Surprisingly
    3.45
    There
    3.39
    In
    3.33
    Surprisingly
    3.30
    On
    3.27
    You
    3.27
    what
    3.23
    Activations Density 0.005%

    No Known Activations