© 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. 34-GEMMASCOPE-RES-131K
    7. 47773
    Prev
    Next
    INDEX
    Explanations

    Category or subcategory names

    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
     reche
    -0.87
    📁
    -0.86
     forem
    -0.85
     recue
    -0.83
     victorias
    -0.82
     quartos
    -0.82
     donar
    -0.80
     Vorteile
    -0.79
    افع
    -0.79
     chevalier
    -0.79
    POSITIVE LOGITS
     subcategory
    1.63
    CategoryName
    1.23
    SubCategory
    1.16
    subcategory
    1.12
    chea
    0.77
    categoryName
    0.76
    ッタ
    0.73
     Homemade
    0.72
     ਤੇ
    0.72
     Piston
    0.71
    Activations Density 0.055%

    No Known Activations