© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68622
    Prev
    Next
    INDEX
    Explanations

    geographical locations and institutions

    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
     world
    -1.09
     worldwide
    -0.95
     textbook
    -0.90
     typique
    -0.88
    coço
    -0.85
     countries
    -0.84
     mankind
    -0.82
    ILAR
    -0.82
     donnés
    -0.82
     authoritative
    -0.81
    POSITIVE LOGITS
    内部
    0.81
     before
    0.79
    旋转
    0.77
    XCTAssert
    0.77
     homemade
    0.77
    :</
    0.76
    гает
    0.75
     trayectoria
    0.75
     mulher
    0.75
    antra
    0.75
    Activations Density 0.116%

    No Known Activations