© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67426
    Prev
    Next
    INDEX
    Explanations

    place names or cities

    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
     ludzie
    -1.72
     favoritas
    -1.56
     システム
    -1.53
    structura
    -1.52
     あります
    -1.51
     عدم
    -1.48
    bước
    -1.48
    大約
    -1.46
     dueños
    -1.46
     potrebbero
    -1.46
    POSITIVE LOGITS
    s
    1.81
    abinieri
    1.44
    ).-
    1.42
    ﹔
    1.39
    isters
    1.38
    岖
    1.38
     `<
    1.37
    enses
    1.37
    inol
    1.36
    逦
    1.36
    Activations Density 0.274%

    No Known Activations