© 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. 119597
    Prev
    Next
    INDEX
    Explanations

    rate of

    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
     Seem
    -1.95
    ↵↵
    -1.95
    妺
    -1.85
    \
    -1.77
     игрушка
    -1.76
    見た
    -1.74
    фов
    -1.66
    ՚
    -1.66
    
    -1.59
     основе
    -1.53
    POSITIVE LOGITS
     rates
    2.47
     deres
    2.30
    ：
    2.22
    訁
    2.03
     THEIR
    1.98
    1.98
    螓
    1.94
     essas
    1.90
    of
    1.88
    氿
    1.84
    Activations Density 0.056%

    No Known Activations