© 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. 117060
    Prev
    Next
    INDEX
    Explanations

    meat and beef cuts

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

    descriptions of food items, especially steaks and meat dishes in restaurant 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
    áñez
    -0.78
    startup
    -0.77
    uevas
    -0.77
     нажмите
    -0.72
     humana
    -0.71
     tetra
    -0.71
     المصرية
    -0.71
     birdie
    -0.71
     hermanas
    -0.70
    ріш
    -0.69
    POSITIVE LOGITS
     steak
    3.22
     steaks
    2.75
     Steak
    2.16
    steak
    2.02
    Steak
    1.92
    🥩
    1.88
     ribe
    1.59
     stake
    1.40
     beef
    1.36
     sir
    1.32
    Activations Density 0.016%

    No Known Activations