© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15692
    Prev
    Next
    INDEX
    Explanations

    plist file structures

    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
     all
    -1.39
     their
    -1.26
     focusing
    -1.20
     this
    -1.18
     with
    -1.16
     create
    -1.16
     many
    -1.13
     provide
    -1.13
     put
    -1.13
     set
    -1.11
    POSITIVE LOGITS
    דיה
    1.28
    そういった
    1.27
    ,;
    1.15
    かというと
    1.14
     énorme
    1.14
    ーズン
    1.13
     メニュー
    1.10
    욤
    1.09
    こういった
    1.09
     geprü
    1.08
    Activations Density 0.000%

    No Known Activations