© 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. 73454
    Prev
    Next
    INDEX
    Explanations

    limit theorem

    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
    -1.05
    worked
    -1.05
     PHILL
    -1.02
    couldn
    -1.01
    never
    -1.01
    lived
    -0.99
     kalender
    -0.99
    commen
    -0.99
    probably
    -0.98
    doses
    -0.98
    POSITIVE LOGITS
     our
    1.27
    unzione
    1.03
    nthetic
    1.02
    鯨
    1.02
     melawan
    1.00
     now
    1.00
    Inggris
    1.00
    さんへ
    1.00
    Stencil
    0.98
     EdgeInsets
    0.97
    Activations Density 0.006%

    No Known Activations