© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34661
    Prev
    Next
    INDEX
    Explanations

    Vielkopolska, Wielkie, Vistupi

    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
    と思ったら
    -0.93
    覚悟
    -0.85
     mettez
    -0.83
    前は
    -0.82
     complica
    -0.77
     untill
    -0.76
     indicando
    -0.76
    謎
    -0.75
    总裁
    -0.75
     fons
    -0.74
    POSITIVE LOGITS
    づけ
    1.00
     ewigen
    0.92
     ві
    0.90
    Ве
    0.90
     Ве
    0.87
     geboten
    0.86
    chern
    0.83
    ilitatea
    0.83
    DTD
    0.82
     különböző
    0.82
    Activations Density 0.004%

    No Known Activations