© 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. 3786
    Prev
    Next
    INDEX
    Explanations

    reconditioned or resurfaced

    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
     MUCH
    -2.70
    ti
    -2.69
     decidi
    -2.66
     permanece
    -2.66
    ଝ
    -2.56
     terá
    -2.44
     pertence
    -2.41
     are
    -2.36
     mantém
    -2.30
     deverá
    -2.28
    POSITIVE LOGITS
    ’
    3.50
    龊
    2.47
    櫚
    2.47
    g
    2.38
     They
    2.38
     форми
    2.34
    .”
    2.33
    
    2.27
    ーズン
    2.27
     Because
    2.27
    Activations Density 0.002%

    No Known Activations