© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100595
    Prev
    Next
    INDEX
    Explanations

    height measurements

    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_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
    Other
    -2.38
    อื่น
    -1.98
    other
    -1.88
     it
    -1.87
     Other
    -1.85
     Also
    -1.80
     different
    -1.77
     otras
    -1.73
    Another
    -1.73
     anderen
    -1.70
    POSITIVE LOGITS
     Ê
    1.75
    ⇡
    1.55
    
    1.55
     gewi
    1.51
    鲠
    1.50
     penchant
    1.44
     myriad
    1.43
     brillantes
    1.40
     morgens
    1.40
     fiasco
    1.39
    Activations Density 0.008%

    No Known Activations