© 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. 34-GEMMASCOPE-RES-131K
    7. 62871
    Prev
    Next
    INDEX
    Explanations

    Indonesian places and organizations

    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_34/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
     Anggota
    -2.03
     Lengkap
    -1.87
     Tentang
    -1.85
     Layanan
    -1.84
     Makanan
    -1.83
     Biaya
    -1.80
     Sakit
    -1.78
     Terbaru
    -1.77
     Manusia
    -1.77
     Pemer
    -1.75
    POSITIVE LOGITS
     Indonesian
    1.84
     Indonesia
    1.79
     dan
    1.41
     aukš
    1.35
    Indonesia
    1.34
     Pel
    1.30
     Pes
    1.30
     virš
    1.29
     prieš
    1.29
     naudo
    1.28
    Activations Density 0.261%

    No Known Activations