© 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. 34-GEMMASCOPE-RES-131K
    7. 108876
    Prev
    Next
    INDEX
    Explanations

    chili peppers and jalapeños

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

    words related to spicy food ingredients, particularly chili peppers and hot pepper varieties.

    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
     Europeans
    -0.83
     outlaw
    -0.77
    ់
    -0.73
     국가
    -0.73
    prj
    -0.73
     maquina
    -0.73
     Euros
    -0.73
    ppery
    -0.72
    milan
    -0.71
     European
    -0.70
    POSITIVE LOGITS
     Verde
    0.84
     Abdu
    0.79
    uate
    0.79
    青
    0.75
     po
    0.75
     Szer
    0.75
     roasted
    0.73
     september
    0.73
    meris
    0.71
    об
    0.70
    Activations Density 0.015%

    No Known Activations