© 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. 10-GEMMASCOPE-RES-131K
    7. 86126
    Prev
    Next
    INDEX
    Explanations

    vehicles and parking

    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_10/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
     of
    -1.68
    ↵
    -1.67
    ».
    -1.38
     ekster
    -1.36
     sisi
    -1.35
    :
    -1.30
     for
    -1.30
    ématiques
    -1.27
     mitu
    -1.27
    .”
    -1.26
    POSITIVE LOGITS
    Salir
    1.26
     Audiodateien
    1.26
     hlavně
    1.23
     wanting
    1.22
     daje
    1.19
    тьми
    1.19
    niająca
    1.18
     hinders
    1.17
     uniquement
    1.16
     zprávy
    1.15
    Activations Density 0.026%

    No Known Activations