© 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. 69982
    Prev
    Next
    INDEX
    Explanations

    raw, living, food, fruit

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

    content related to food, nutrition, and dietary practices.

    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
    sendTo
    -0.75
     feathered
    -0.75
     Rodeo
    -0.75
     notwendi
    -0.73
    وة
    -0.73
     latte
    -0.70
     Росси
    -0.68
    ensioni
    -0.68
     Murillo
    -0.68
     ouder
    -0.66
    POSITIVE LOGITS
     raw
    1.02
     Raw
    0.93
     fruit
    0.92
    もちゃ
    0.87
     leben
    0.87
    Raw
    0.86
    raw
    0.83
    Fruit
    0.82
     RAW
    0.81
    nack
    0.79
    Activations Density 0.016%

    No Known Activations