© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73744
    Prev
    Next
    INDEX
    Explanations

    foreign names and academic citations

    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
     might
    -0.93
     componentes
    -0.91
     radioactivity
    -0.85
     computerized
    -0.84
    اصمة
    -0.83
    oksi
    -0.83
     dormitorios
    -0.82
     Though
    -0.81
     इस्त
    -0.80
    気で
    -0.80
    POSITIVE LOGITS
     FILMS
    1.23
     facile
    1.09
    ostruct
    1.07
    兲
    1.05
     ә
    1.02
     maneiras
    0.96
    
    0.95
    CLEAN
    0.94
    ammlung
    0.93
    función
    0.91
    Activations Density 0.019%

    No Known Activations