© 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. 31194
    Prev
    Next
    INDEX
    Explanations

    BMW motorcycles and women's health

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

    alphanumeric model numbers and technical specifications, particularly for vehicles and technical systems.

    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
     MOL
    -0.85
    Tensi
    -0.80
     Gass
    -0.75
    vati
    -0.73
    CommandHandler
    -0.72
     hunters
    -0.71
     Verarbeitung
    -0.69
    Raymond
    -0.69
    isFile
    -0.69
    Jeffrey
    -0.69
    POSITIVE LOGITS
     BMW
    1.15
    BMW
    1.01
    cú
    0.81
     bmw
    0.79
    bmw
    0.78
    aş
    0.74
    preco
    0.74
     astronaut
    0.71
     Munich
    0.70
     ESA
    0.70
    Activations Density 0.006%

    No Known Activations