© 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. 13201
    Prev
    Next
    INDEX
    Explanations

    multi-lingual common words

    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
     juſ
    -1.43
     zrobić
    -1.38
     devine
    -1.35
     芋
    -1.33
    hemd
    -1.32
    sakura
    -1.31
    ’
    -1.31
    📖
    -1.30
     poncho
    -1.30
    適量
    -1.27
    POSITIVE LOGITS
    さんも
    1.65
    有意思
    1.63
    also
    1.55
     canadienne
    1.52
    話は
    1.52
     we
    1.48
    返す
    1.48
     also
    1.48
     Also
    1.46
     také
    1.45
    Activations Density 0.013%

    No Known Activations