© 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. 130638
    Prev
    Next
    INDEX
    Explanations

    medical conditions and performance

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

    quotations or direct speech in sports and news articles.

    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_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
     illet
    -1.30
    vriende
    -1.30
     konnten
    -1.26
     encontré
    -1.18
     graciosas
    -1.16
     altres
    -1.15
     sartén
    -1.14
     ainda
    -1.13
    ۷
    -1.12
    ⋁
    -1.12
    POSITIVE LOGITS
     differences
    1.46
    𓏸
    1.43
     changes
    1.30
     pelatih
    1.27
     different
    1.22
    !***
    1.20
    ⎯
    1.18
    omaly
    1.17
    を行います
    1.17
     difference
    1.16
    Activations Density 0.017%

    No Known Activations