© 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. 10-GEMMASCOPE-RES-131K
    4. 48377
    Prev
    Next
    INDEX
    Explanations

    organizations, coalitions, alliances, forums

    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
    Leírás
    -1.57
     acabados
    -1.57
     enviable
    -1.53
     zimowe
    -1.51
     sozialen
    -1.51
     verkau
    -1.50
    zdroj
    -1.48
     bekan
    -1.48
    这家伙
    -1.48
     ujedno
    -1.47
    POSITIVE LOGITS
     by
    1.53
     :}
    1.51
     ")[
    1.45
     have
    1.41
     “
    1.39
    ;");
    1.39
    '></
    1.37
     there
    1.36
     would
    1.32
     then
    1.31
    Activations Density 0.066%

    No Known Activations