© 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. 119332
    Prev
    Next
    INDEX
    Explanations

    more, comparison, quantity

    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
     ||
    
    -1.03
     ܠ
    -0.93
    高达
    -0.92
    Faster
    -0.92
     分页
    -0.91
    ">*</
    -0.91
    گانه
    -0.91
    annels
    -0.90
    ництво
    -0.90
    zzá
    -0.90
    POSITIVE LOGITS
     more
    7.34
    more
    4.13
     più
    3.98
     более
    3.73
     más
    3.66
    More
    3.56
     lebih
    3.45
     больше
    3.34
     більше
    3.31
     mehr
    3.28
    Activations Density 0.116%

    No Known Activations