© 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. 128362
    Prev
    Next
    INDEX
    Explanations

    consequence or continuation

    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
     или
    -1.18
     obuv
    -1.16
     peut
    -1.16
     "}";
    -1.16
     например
    -1.15
    ־ה
    -1.12
     景色
    -1.11
    itário
    -1.09
     hatta
    -1.08
     vagy
    -1.05
    POSITIVE LOGITS
     therefore
    1.31
     then
    1.30
     thus
    1.27
     thereby
    1.13
     resulting
    1.12
    সূত্র
    1.05
     process
    1.05
    क्रिया
    1.05
     iveco
    1.05
     Indem
    1.03
    Activations Density 0.109%

    No Known Activations