© 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. 124146
    Prev
    Next
    INDEX
    Explanations

    gaze direction

    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
     Если
    -1.90
     Unless
    -1.88
    ueling
    -1.80
     Either
    -1.77
    Surprisingly
    -1.74
     Neither
    -1.73
    ynı
    -1.70
     Interestingly
    -1.70
    Both
    -1.66
    Interestingly
    -1.66
    POSITIVE LOGITS
     '
    1.71
    👀
    1.70
     the
    1.63
     👀
    1.59
    look
    1.55
     intently
    1.55
     personnels
    1.50
    '
    1.50
     ï
    1.49
     aires
    1.45
    Activations Density 0.099%

    No Known Activations