© 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. 10-GEMMASCOPE-RES-131K
    7. 72898
    Prev
    Next
    INDEX
    Explanations

    error or missing dependencies

    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
    我們
    -1.89
     commentaires
    -1.55
     علاوه
    -1.54
    我们
    -1.51
    usschuss
    -1.50
    uoš
    -1.49
    虽然
    -1.47
    zehnten
    -1.45
     générations
    -1.44
     десер
    -1.43
    POSITIVE LOGITS
     by
    2.56
     when
    1.91
     on
    1.82
     in
    1.81
     or
    1.63
    ;
    1.58
     through
    1.58
     this
    1.56
     all
    1.55
     from
    1.51
    Activations Density 0.766%

    No Known Activations