© 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. 75560
    Prev
    Next
    INDEX
    Explanations

    gene variant or polymorphism

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

    numerical identifiers and values in genetic and technical contexts.

    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_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
    也不會
    -0.90
    旁邊
    -0.86
     chúc
    -0.85
    總是
    -0.84
    欣賞
    -0.81
    thiet
    -0.81
    並不
    -0.78
     when
    -0.77
    也沒有
    -0.77
     Donuts
    -0.76
    POSITIVE LOGITS
     help
    1.86
    help
    1.61
    HELP
    1.58
     HELP
    1.54
     ayuda
    1.35
    Help
    1.29
     Help
    1.27
     PLEASE
    1.26
    HEL
    1.20
    PLEASE
    1.17
    Activations Density 0.015%

    No Known Activations