© 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. 79874
    Prev
    Next
    INDEX
    Explanations

    food, materials, transformations, or medical contexts

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

    references to content or objects contained within other things.

    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
     emphasis
    -0.93
     on
    -0.84
    に対する
    -0.83
     taxis
    -0.81
    Where
    -0.81
     during
    -0.79
     त्र
    -0.78
     knot
    -0.78
     knotted
    -0.77
    듭
    -0.77
    POSITIVE LOGITS
     that
    1.27
     contains
    1.20
     Contains
    0.97
    variance
    0.97
    APOLIS
    0.97
    graphique
    0.96
     Contain
    0.96
     contain
    0.96
     bawat
    0.95
     इस्त
    0.94
    Activations Density 0.104%

    No Known Activations