© 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. 22-GEMMASCOPE-RES-131K
    7. 36562
    Prev
    Next
    INDEX
    Explanations

    code block openings

    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_22/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
     Tutti
    -1.11
    🏧
    -1.09
    ológico
    -1.07
     kemeja
    -1.05
     triko
    -1.04
    masyarakat
    -1.04
     blusas
    -1.02
    ógico
    -1.02
    tarjetas
    -1.02
     about
    -1.01
    POSITIVE LOGITS
    头部
    0.94
     vechi
    0.93
    ↵↵
    0.90
    ambut
    0.90
    想不到
    0.88
    existsSync
    0.88
     variétés
    0.87
     has
    0.87
    没办法
    0.86
    楽しみ
    0.84
    Activations Density 0.003%

    No Known Activations