© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16538
    Prev
    Next
    INDEX
    Explanations

    PHP database utilities

    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
    Negative Logits
     anything
    -1.19
     cidades
    -1.13
     caminar
    -1.11
    ternut
    -1.03
     LayoutInflater
    -1.03
     everything
    -1.02
     hombro
    -1.01
     encontraron
    -1.01
     Psychologie
    -1.00
    Açık
    -0.98
    POSITIVE LOGITS
    겟
    0.98
    ✨✨
    0.92
    🔥🔥
    0.91
    Мой
    0.90
     Curs
    0.89
    😓
    0.89
     Menor
    0.88
    🙋
    0.87
     methods
    0.87
     Prepar
    0.87
    Activations Density 0.007%

    No Known Activations