© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117321
    Prev
    Next
    INDEX
    Explanations

    genetic 'rs' variants or code triggers

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

    reference IDs (rs numbers) in genetic research papers and jQuery trigger events.

    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
    ptime
    -0.73
     Confederacy
    -0.73
    WEDNESDAY
    -0.70
    NOR
    -0.69
    lorum
    -0.68
     specifications
    -0.68
    camore
    -0.68
     spotted
    -0.67
     zd
    -0.67
    偏
    -0.66
    POSITIVE LOGITS
    sión
    0.68
    única
    0.68
     solle
    0.68
     Coyle
    0.67
    expend
    0.66
    jutkan
    0.66
     gérer
    0.65
     cipolla
    0.64
    Hector
    0.64
     sors
    0.63
    Activations Density 0.110%

    No Known Activations