© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27444
    Prev
    Next
    INDEX
    Explanations

    voltage, percent, sheet

    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
     Игра
    -1.02
     Какой
    -0.99
     Что
    -0.91
     Работа
    -0.90
    電腦
    -0.90
     tehd
    -0.90
     of
    -0.88
     näky
    -0.88
     Как
    -0.86
     Одно
    -0.84
    POSITIVE LOGITS
     demora
    0.94
     victories
    0.93
     taux
    0.88
    切る
    0.88
    vedra
    0.88
     matricula
    0.87
    Instrucciones
    0.87
     iload
    0.86
    nă
    0.85
    °;
    0.85
    Activations Density 0.064%

    No Known Activations