© 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. 27349
    Prev
    Next
    INDEX
    Explanations

    code and math symbols

    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
    τερ
    -1.00
     recetas
    -0.94
    ifolia
    -0.94
    outfit
    -0.93
    حل
    -0.92
     蓋
    -0.90
    songwriter
    -0.89
     Temporada
    -0.88
     peliculas
    -0.88
     individuel
    -0.87
    POSITIVE LOGITS
     on
    1.03
     that
    1.02
     easy
    0.93
     is
    0.92
    engarkan
    0.88
    倖
    0.86
    Сю
    0.85
    cosmos
    0.85
    what
    0.84
     Sehr
    0.84
    Activations Density 0.002%

    No Known Activations