© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20892
    Prev
    Next
    INDEX
    Explanations

    ultraviolet or thereof

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

    technical procedures in scientific or industrial processes, particularly when describing steps, methods, or treatments.

    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
    romeda
    -1.78
    ternut
    -1.70
    rogens
    -1.64
    termilk
    -1.63
     who
    -1.58
    轵
    -1.56
     their
    -1.51
    terscotch
    -1.50
     الذين
    -1.49
    
    -1.48
    POSITIVE LOGITS
    .
    1.75
     ausdrück
    1.54
     akzep
    1.35
    zeß
    1.34
     Lainnya
    1.34
     två
    1.30
    போ
    1.27
    ircut
    1.27
     nové
    1.27
    ilih
    1.25
    Activations Density 0.244%

    No Known Activations