© 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. 99608
    Prev
    Next
    INDEX
    Explanations

    numbers after hyphens

    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
     the
    -3.34
    —
    -2.56
     After
    -2.38
    -
    -2.27
     типи
    -2.13
     Normally
    -2.11
     После
    -2.09
     这
    -2.09
     mammoth
    -2.06
     With
    -2.05
    POSITIVE LOGITS
    1
    3.27
    蕺
    2.98
    旰
    2.86
    骉
    2.83
    玬
    2.78
    ಱ
    2.78
    鲧
    2.70
    䛗
    2.69
    玕
    2.67
    
    2.64
    Activations Density 0.864%

    No Known Activations