© 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. 22-GEMMASCOPE-RES-131K
    7. 104494
    Prev
    Next
    INDEX
    Explanations

    long days, hard work

    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
     one
    -1.05
     by
    -1.02
     as
    -1.02
    arono
    -0.96
     Wors
    -0.95
    ↵↵↵
    -0.90
    byId
    -0.90
    haped
    -0.89
    uvres
    -0.88
    ()),
    -0.86
    POSITIVE LOGITS
    Either
    1.02
     упражнения
    0.99
    reichen
    0.99
    或
    0.98
    muje
    0.97
    komen
    0.96
     tiring
    0.96
    が必要です
    0.94
    Been
    0.92
    おわりに
    0.92
    Activations Density 0.019%

    No Known Activations