© 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. 22-GEMMASCOPE-RES-131K
    7. 73067
    Prev
    Next
    INDEX
    Explanations

    country

    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_22/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
     propias
    -1.16
    giai
    -1.07
    :{
    -1.07
    /*",
    -1.05
    )},
    -1.03
    
    -1.03
    ⦃
    -1.01
    逛
    -1.00
    /',
    -1.00
    inois
    -1.00
    POSITIVE LOGITS
     countries
    1.66
     country
    1.30
    worpen
    1.26
    Countries
    1.25
     nations
    1.25
     international
    1.21
     nationality
    1.21
     powiedzieć
    1.16
    atasi
    1.16
    Муж
    1.07
    Activations Density 0.008%

    No Known Activations