© 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. 11283
    Prev
    Next
    INDEX
    Explanations

    system components and concepts

    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
    üller
    -1.41
    Şi
    -1.41
     ikke
    -1.39
     divertido
    -1.34
    谒
    -1.33
     mépris
    -1.32
    ppchen
    -1.28
     sentir
    -1.28
     seura
    -1.27
     repuesto
    -1.27
    POSITIVE LOGITS
     which
    2.59
     of
    2.34
     but
    1.70
     in
    1.56
     who
    1.48
     like
    1.38
     by
    1.33
     due
    1.31
     so
    1.27
     especially
    1.26
    Activations Density 0.283%

    No Known Activations