© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60519
    Prev
    Next
    INDEX
    Explanations

    introducing lists of examples

    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
    There
    -1.85
     они
    -1.62
     Although
    -1.59
     This
    -1.58
    n
    -1.58
     has
    -1.58
     Sometimes
    -1.58
    Those
    -1.58
     Those
    -1.56
    9
    -1.52
    POSITIVE LOGITS
     barva
    1.74
     bén
    1.70
     ง
    1.70
    และ
    1.63
     одной
    1.55
     ráp
    1.55
     rése
    1.52
     dupla
    1.52
    絝
    1.51
     fizer
    1.50
    Activations Density 0.045%

    No Known Activations