© 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. 130904
    Prev
    Next
    INDEX
    Explanations

    special characters or abbreviations

    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
     or
    -1.50
     and
    -1.48
     '
    -1.40
    あるいは
    -1.34
     in
    -1.28
     with
    -1.26
     so
    -1.23
     aud
    -1.19
     bzw
    -1.17
     all
    -1.16
    POSITIVE LOGITS
     empêcher
    1.77
    也在
    1.54
    Auch
    1.49
     déposer
    1.48
     kuiten
    1.43
    лися
    1.40
    깽
    1.36
    휀
    1.35
     terminer
    1.35
     condamné
    1.34
    Activations Density 0.206%

    No Known Activations