© 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. 127474
    Prev
    Next
    INDEX
    Explanations

    following "Additionally,"

    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
     
    -2.58
     after
    -1.87
     With
    -1.85
    in
    -1.84
     In
    -1.84
    me
    -1.80
     Both
    -1.80
    ↵↵↵
    -1.80
     However
    -1.77
     even
    -1.76
    POSITIVE LOGITS
    鮡
    2.11
    
    2.08
     you
    2.05
     汽车
    1.96
     incrí
    1.95
     vôtre
    1.89
    踯
    1.86
    ჱ
    1.80
    Ꮠ
    1.79
    鱻
    1.75
    Activations Density 0.025%

    No Known Activations