© 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. 69819
    Prev
    Next
    INDEX
    Explanations

    names of chefs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    zyw
    -0.91
     hardware
    -0.84
    tyw
    -0.82
    態度
    -0.79
    deal
    -0.77
     badań
    -0.77
    子を
    -0.77
     editors
    -0.74
     consumer
    -0.74
     secrétaire
    -0.73
    POSITIVE LOGITS
     chef
    2.56
     Chef
    2.28
    Chef
    2.11
     chefs
    2.08
    chef
    1.88
     Chefs
    1.74
     Michelin
    1.41
     restaur
    1.34
     michelin
    1.27
    chefs
    1.17
    Activations Density 0.028%

    No Known Activations