© 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. 34-GEMMASCOPE-RES-131K
    7. 117878
    Prev
    Next
    INDEX
    Explanations

    closing tags

    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
     proceeded
    -0.81
     типа
    -0.72
     proceed
    -0.71
    trt
    -0.69
     surround
    -0.69
     assisting
    -0.69
     mágica
    -0.68
     하고
    -0.68
     todays
    -0.67
     Bik
    -0.67
    POSITIVE LOGITS
    lllllll
    0.96
    🥎
    0.93
    </i>
    0.90
    </
    0.85
    èze
    0.84
    Whoosh
    0.84
    rspec
    0.84
    Especificações
    0.83
    >[]
    0.83
     чинов
    0.83
    Activations Density 0.012%

    No Known Activations