© 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. 44757
    Prev
    Next
    INDEX
    Explanations

    international words and place names

    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
     mencegah
    -1.75
     that
    -1.66
    vyšší
    -1.59
    ſtra
    -1.49
     potranno
    -1.47
     Sauerstoff
    -1.46
     mengatasi
    -1.45
     jotka
    -1.45
    lepší
    -1.45
    0
    -1.44
    POSITIVE LOGITS
     in
    2.36
     into
    1.67
    -
    1.60
    sly
    1.55
    こんな
    1.41
    鈁
    1.37
    广西
    1.37
    mercedes
    1.35
    germany
    1.35
    パリ
    1.30
    Activations Density 0.107%

    No Known Activations