© 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. 128170
    Prev
    Next
    INDEX
    Explanations

    great emphasis

    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
     творо
    -1.10
     шокола
    -1.09
    摁
    -1.02
    是怎么回事
    -1.02
     cliquer
    -1.01
    казания
    -0.99
    tillerie
    -0.99
    нете
    -0.99
     guatemala
    -0.97
     сыром
    -0.96
    POSITIVE LOGITS
     almendras
    1.14
     variedades
    1.10
    ด้วย
    1.09
     treff
    1.09
    בח
    1.07
     крепления
    1.05
    ungsanleitung
    1.01
    ０
    0.98
    Agree
    0.97
    fır
    0.96
    Activations Density 0.006%

    No Known Activations