© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71153
    Prev
    Next
    INDEX
    Explanations

    protein and nutrition

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

    protein intake and satiety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    墺
    0.48
    argeon
    0.47
     तीर
    0.46
     गुलाब
    0.46
    ොර
    0.45
     свето
    0.44
    鄞
    0.44
    鏑
    0.44
     Adası
    0.44
    諄
    0.44
    POSITIVE LOGITS
     protein
    1.42
    Protein
    1.34
     Protein
    1.29
    protein
    1.24
     प्रोटीन
    1.14
     proteins
    1.05
     Proteins
    1.05
    proteins
    1.02
     proteine
    1.00
    蛋白質
    0.99
    Activations Density 0.177%

    No Known Activations