© 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. 79126
    Prev
    Next
    INDEX
    Explanations

    satellite

    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
    计时
    -0.88
     Cárdenas
    -0.81
    solutions
    -0.77
    ziek
    -0.76
    digans
    -0.76
     altro
    -0.76
    禺
    -0.76
    ännande
    -0.75
    CJK
    -0.75
    glades
    -0.73
    POSITIVE LOGITS
     satellite
    4.75
     satellites
    4.63
     Satellite
    3.50
    satellite
    3.34
    Satellite
    3.34
     Satellites
    3.31
    卫星
    2.95
     satel
    2.86
    Sat
    2.81
    sat
    2.75
    Activations Density 0.068%

    No Known Activations