© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129886
    Prev
    Next
    INDEX
    Explanations

    organized events and activities

    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
     not
    -1.55
     некоторых
    -1.50
     некоторы
    -1.44
     most
    -1.40
     Instead
    -1.35
    出来ました
    -1.34
     instead
    -1.27
    頂いた
    -1.27
     zamiast
    -1.26
     posiblemente
    -1.25
    POSITIVE LOGITS
     such
    1.56
    "",
    1.36
    kız
    1.33
     såsom
    1.31
     Chaque
    1.30
    comune
    1.27
     SUCH
    1.23
     vinter
    1.23
     each
    1.22
    ViewChild
    1.21
    Activations Density 0.062%

    No Known Activations