© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15139
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    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
     in
    -2.06
     is
    -1.45
     still
    -1.40
     from
    -1.30
     by
    -1.30
             
    -1.30
     it
    -1.27
    1
    -1.25
    不同
    -1.25
     as
    -1.21
    POSITIVE LOGITS
    　“
    1.51
     pantalón
    1.43
     仕事
    1.39
    翾
    1.34
     yelek
    1.34
    儛
    1.34
     manifiesto
    1.31
    奩
    1.27
     Trouver
    1.27
     wers
    1.27
    Activations Density 0.032%

    No Known Activations