© 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. 22169
    Prev
    Next
    INDEX
    Explanations

    endoscopic procedures and food items

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

    words related to food items, particularly different types of pancakes, pastries, and bread products.

    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_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
    
    -2.63
    剷
    -2.38
    很久
    -2.28
    Ꮉ
    -2.25
    が欲しい
    -2.23
    新しく
    -2.22
    摳
    -2.22
    ین
    -2.20
     botão
    -2.19
    也沒
    -2.19
    POSITIVE LOGITS
    釭
    2.14
    i
    1.93
     Figure
    1.87
     Get
    1.82
     …
    1.81
     In
    1.80
     Е
    1.73
     for
    1.71
     As
    1.70
    lancer
    1.68
    Activations Density 0.003%

    No Known Activations