© 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. 10-GEMMASCOPE-RES-131K
    7. 47582
    Prev
    Next
    INDEX
    Explanations

    veto powers

    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
     \
    -2.70
    ?
    -2.45
    ين
    -2.27
    «
    -2.14
     We
    -2.14
     設計
    -2.11
    en
    -2.02
    镰
    -1.91
    da
    -1.91
    翃
    -1.88
    POSITIVE LOGITS
    枼
    2.17
     helicópter
    2.02
     sebaik
    2.02
     défis
    1.99
     botol
    1.98
     sementara
    1.96
    حدى
    1.96
     resmi
    1.96
     prépare
    1.91
    ྜ
    1.90
    Activations Density 0.001%

    No Known Activations