© 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. 22-GEMMASCOPE-RES-131K
    4. 70741
    Prev
    Next
    INDEX
    Explanations

    column definitions

    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_22/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
     as
    -1.17
     in
    -0.95
     or
    -0.91
     when
    -0.90
     帝
    -0.89
     although
    -0.88
     October
    -0.87
     and
    -0.86
     When
    -0.86
     most
    -0.85
    POSITIVE LOGITS
     '.')
    0.99
     сосед
    0.97
     laiss
    0.96
    cún
    0.95
    ᄍ
    0.94
     Tienen
    0.94
    rija
    0.94
    ᒍ
    0.93
    өздер
    0.93
     renaissance
    0.93
    Activations Density 0.000%

    No Known Activations