© 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. 33874
    Prev
    Next
    INDEX
    Explanations

    upcoming championship events

    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
     السياس
    -2.03
     економі
    -1.44
    祂
    -1.42
    música
    -1.34
    民众
    -1.33
    breos
    -1.32
     الحكومة
    -1.31
    uchten
    -1.29
     الخدم
    -1.28
     cristianismo
    -1.27
    POSITIVE LOGITS
     your
    1.40
     upcoming
    1.39
     coaching
    1.35
    可能
    1.32
     championship
    1.30
     will
    1.27
     possible
    1.27
     блюдо
    1.27
     Championship
    1.24
     also
    1.23
    Activations Density 0.042%

    No Known Activations