© 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. 65314
    Prev
    Next
    INDEX
    Explanations

    various different languages

    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
     with
    -1.17
     these
    -1.16
     Only
    -1.12
    silience
    -1.11
    балан
    -1.04
    __":
    -1.01
     more
    -1.00
     our
    -0.98
     кг
    -0.97
     צילום
    -0.95
    POSITIVE LOGITS
     различных
    1.18
     verschillende
    1.14
     poft
    1.13
    隂
    1.12
     seinem
    1.11
    
    1.11
     distintos
    1.10
     diversos
    1.09
     diferentes
    1.08
     różnych
    1.05
    Activations Density 0.005%

    No Known Activations