© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73771
    Prev
    Next
    INDEX
    Explanations

    egg coating or brushing

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

    ingredient measurements and quantities in recipes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    کیل
    -0.84
     Insol
    -0.82
    DET
    -0.82
    ﺼ
    -0.78
    siers
    -0.77
    Fitted
    -0.77
    orphic
    -0.75
    unpack
    -0.74
     Aleksandr
    -0.74
    deserialize
    -0.71
    POSITIVE LOGITS
     egg
    1.17
     beaten
    1.09
     coat
    1.06
     brush
    0.99
     Coating
    0.98
     coating
    0.98
     Coat
    0.93
    coating
    0.92
     Egg
    0.89
     brushing
    0.88
    Activations Density 0.008%

    No Known Activations