© 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. 63079
    Prev
    Next
    INDEX
    Explanations

    food items and dishes

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

    The neuron fires wherever a restaurant‐style menu item is being listed—especially ingredient or dish descriptions in parentheses or quotes.

    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
    ommt
    -1.08
    ComponentScan
    -1.05
     птиц
    -1.02
    ꦿ
    -0.98
    ₓ
    -0.96
    licopter
    -0.95
     ポケモン
    -0.95
    ruit
    -0.94
    poner
    -0.94
     obstante
    -0.94
    POSITIVE LOGITS
     our
    1.61
     your
    1.21
    我們的
    1.05
     with
    1.04
     served
    0.98
    your
    0.96
     Our
    0.95
     nuestros
    0.92
     nuestro
    0.91
    our
    0.90
    Activations Density 0.016%

    No Known Activations