© 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. 70780
    Prev
    Next
    INDEX
    Explanations

    technical concepts and code

    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
     серебри
    -0.98
    ࣭
    -0.98
     Añade
    -0.95
     शुर
    -0.94
     this
    -0.93
    靄
    -0.93
     four
    -0.90
    右侧
    -0.90
     там
    -0.90
     zonas
    -0.88
    POSITIVE LOGITS
     peculiarly
    1.11
     unbelievably
    1.10
    namespace
    1.01
     trône
    0.99
    ã
    0.96
     alluring
    0.96
    ativna
    0.95
     exceptionally
    0.95
     новое
    0.94
     хорошее
    0.92
    Activations Density 0.243%

    No Known Activations