© 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. 38344
    Prev
    Next
    INDEX
    Explanations

    United States years

    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
     Dí
    -1.14
     negatif
    -1.02
     Musée
    -1.01
    ::{
    -0.97
    Гц
    -0.96
     minta
    -0.94
    –¿
    -0.94
     inclut
    -0.94
     Ön
    -0.93
     процес
    -0.92
    POSITIVE LOGITS
     parlare
    1.09
     parlato
    0.99
    改为
    0.93
     abends
    0.93
    ared
    0.92
     guadag
    0.91
    院校
    0.91
    IDENTAL
    0.90
     имеется
    0.90
     doğal
    0.90
    Activations Density 0.029%

    No Known Activations