© 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. 26058
    Prev
    Next
    INDEX
    Explanations

    sports actions and results

    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
    ducers
    -1.23
    幛
    -1.17
     it
    -1.15
     además
    -1.06
     ARISING
    -1.01
    Bild
    -1.00
     május
    -1.00
    えません
    -0.99
    trains
    -0.99
    pters
    -0.99
    POSITIVE LOGITS
    зом
    1.05
     during
    1.05
    こんにちは
    1.02
     at
    1.01
    conio
    0.99
    xtext
    0.99
    などなど
    0.98
     Cleanser
    0.96
     succes
    0.96
    UNICIP
    0.96
    Activations Density 0.010%

    No Known Activations