© 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. 31472
    Prev
    Next
    INDEX
    Explanations

    meat and meatballs

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

    food-related terms and descriptions, particularly meat items and culinary dishes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on words that are parts of meat‐based dish names (e.g. “spaghetti and meatballs,” “smashed burgers,” “meat loaf,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Bassi
    -0.87
     HSE
    -0.81
     Xamarin
    -0.79
     Compile
    -0.78
    ሮ
    -0.77
    EDY
    -0.75
     AUT
    -0.74
    蹬
    -0.74
     Dunlop
    -0.73
     epson
    -0.73
    POSITIVE LOGITS
     meat
    1.82
     Meat
    1.55
     ground
    1.51
     meatballs
    1.41
     Ground
    1.41
    meat
    1.38
    Meat
    1.38
     beef
    1.38
    Ground
    1.29
     Beef
    1.26
    Activations Density 0.017%

    No Known Activations