© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23633
    Prev
    Next
    INDEX
    Explanations

    food ingredients and pairings

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

    food ingredients and flavors in recipes, particularly focusing on specific food items and flavor combinations.

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

    The neuron activates on words naming food items or ingredients.

    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
     namorado
    -1.00
    gico
    -0.96
     deputado
    -0.93
     ARISING
    -0.92
     colega
    -0.90
     asfal
    -0.89
     ſtre
    -0.88
     soooo
    -0.88
     sooo
    -0.87
     secrétaire
    -0.86
    POSITIVE LOGITS
     and
    1.80
     &
    1.03
     based
    0.94
     with
    0.93
    &
    0.88
     każde
    0.82
     flavor
    0.81
     Before
    0.80
     goes
    0.78
    gulama
    0.77
    Activations Density 0.021%

    No Known Activations