© 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. 70422
    Prev
    Next
    INDEX
    Explanations

    high court, Centre, operator

    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
     suatu
    -1.40
     our
    -1.32
     hatta
    -1.26
    ほんとに
    -1.25
     avantaj
    -1.24
     célè
    -1.21
    凄く
    -1.21
     VizieR
    -1.19
     astu
    -1.17
    沵
    -1.17
    POSITIVE LOGITS
    ַּ
    1.77
    ּוֹ
    1.63
    说法
    1.44
    וּ
    1.39
    ְּ
    1.36
    zło
    1.33
     five
    1.31
    ָּ
    1.29
    ִּ
    1.29
     Wednesday
    1.27
    Activations Density 0.028%

    No Known Activations