© 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. 65590
    Prev
    Next
    INDEX
    Explanations

    URLs, HTML attributes, and file paths

    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
    nae
    -1.03
    igth
    -0.99
     expectativa
    -0.95
     RECOMEND
    -0.93
    での
    -0.91
     deine
    -0.88
     escolares
    -0.87
     oth
    -0.87
    Parece
    -0.87
     コットン
    -0.86
    POSITIVE LOGITS
    いかがでしたか
    1.07
     Хай
    1.05
    ございました
    1.02
    quarelle
    1.02
     СЕ
    1.00
     HTTP
    0.99
    に行って
    0.99
    fusions
    0.97
     url
    0.97
     Гі
    0.97
    Activations Density 0.009%

    No Known Activations