© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40391
    Prev
    Next
    INDEX
    Explanations

    code, programming, object-oriented, language constructs

    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
     Վերցված
    -1.17
     TAMBÉM
    -1.14
    сила
    -1.12
    бѣ
    -1.08
     sérieux
    -1.08
     φα
    -1.05
     zarówno
    -1.04
    cati
    -1.04
    リット
    -1.03
    дости
    -1.03
    POSITIVE LOGITS
     or
    1.20
     and
    1.18
    差别
    0.98
     immaculate
    0.98
     проник
    0.98
    izacji
    0.97
    ugas
    0.95
     invaluable
    0.95
    cachor
    0.91
    晌
    0.91
    Activations Density 0.005%

    No Known Activations