© 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. 10-GEMMASCOPE-RES-131K
    7. 128313
    Prev
    Next
    INDEX
    Explanations

    food ingredients and condiments

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

    words related to food seasonings and condiments, particularly Asian sauces and ingredients.

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

    The neuron fires on numeric tokens—especially quantities in recipes (tablespoon counts, weights, concentrations) and other measurement figures in scientific contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -1.69
     Если
    -1.68
     This
    -1.63
    chränkungen
    -1.60
     Each
    -1.59
     hitta
    -1.57
    鯔
    -1.55
     There
    -1.55
     They
    -1.52
     Это
    -1.51
    POSITIVE LOGITS
    _
    1.69
     Entfer
    1.66
     Vorgang
    1.63
     別注
    1.51
     Öffnen
    1.47
     Können
    1.45
    Remarque
    1.42
     ダブル
    1.40
     ワン
    1.40
     kolejny
    1.38
    Activations Density 0.010%

    No Known Activations