© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130863
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    geographic locations and academic/technical terms in scientific or historical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     berge
    -0.98
    耵
    -0.97
    odorant
    -0.95
     industrielle
    -0.94
     alumno
    -0.94
     difficultés
    -0.94
     eenig
    -0.94
     véhic
    -0.94
    来看看
    -0.93
     росій
    -0.92
    POSITIVE LOGITS
     would
    1.71
     could
    1.47
     was
    1.47
     make
    1.46
     is
    1.39
     are
    1.38
     will
    1.37
     include
    1.36
     made
    1.29
     might
    1.21
    Activations Density 0.203%

    No Known Activations