© 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. 28508
    Prev
    Next
    INDEX
    Explanations

    package and state declarations

    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
    **/
    -1.31
     такая
    -1.29
     ferrovia
    -1.27
     måde
    -1.26
     afectar
    -1.19
    Pozdrawiam
    -1.18
    kı
    -1.16
    -",
    -1.16
    "+
    -1.16
     blusa
    -1.15
    POSITIVE LOGITS
    u
    1.41
     of
    1.33
    and
    1.27
    ik
    1.23
    om
    1.22
    or
    1.21
     &
    1.19
    1
    1.16
    man
    1.16
    7
    1.13
    Activations Density 0.001%

    No Known Activations