© 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. 22-GEMMASCOPE-RES-131K
    7. 34794
    Prev
    Next
    INDEX
    Explanations

    command line tools

    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
     biela
    -1.72
     histó
    -1.70
     Projektu
    -1.65
    junge
    -1.64
     hisz
    -1.63
     salonu
    -1.61
     októ
    -1.60
    ᐳ
    -1.60
    ledad
    -1.59
     Muzeum
    -1.59
    POSITIVE LOGITS
     now
    1.52
    1.42
         
    1.37
     not
    1.31
     so
    1.29
     to
    1.26
     get
    1.26
    欣赏
    1.23
    !
    1.22
    D
    1.16
    Activations Density 0.044%
    No Known Activations