© 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. 110629
    Prev
    Next
    INDEX
    Explanations

    round trip

    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
    
    -2.02
     faltan
    -1.82
     aisladas
    -1.77
    越来越多
    -1.75
     tiveram
    -1.75
    岨
    -1.73
     seleccionamos
    -1.73
     “
    -1.72
    犼
    -1.66
     ”
    -1.66
    POSITIVE LOGITS
    ſelves
    2.53
    The
    2.19
    These
    2.00
    引言
    1.90
    雪花
    1.88
    摃
    1.86
    未完
    1.84
    They
    1.83
    Then
    1.80
    This
    1.77
    Activations Density 0.002%

    No Known Activations