© 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. 13043
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and exponents

    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
     AUTOM
    -1.66
    幾天
    -1.52
    ری
    -1.46
    (*´
    -1.46
    **************
    -1.45
     traductions
    -1.41
    ро
    -1.41
     такие
    -1.41
    -----------
    -1.40
     verzorg
    -1.39
    POSITIVE LOGITS
    </em>
    1.81
     has
    1.55
     of
    1.48
     et
    1.43
    нци
    1.41
     you
    1.34
     by
    1.34
     mecán
    1.34
    伥
    1.30
    쐈
    1.30
    Activations Density 0.065%

    No Known Activations