© 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. 8069
    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
     this
    -1.50
    </td>
    -1.39
    🗿
    -1.38
    when
    -1.35
     arī
    -1.34
    inafter
    -1.32
     Since
    -1.30
     اكتوبر
    -1.28
     mengenai
    -1.27
    也有
    -1.27
    POSITIVE LOGITS
    0
    1.66
     we
    1.60
    “
    1.48
    irmanship
    1.48
     maravill
    1.41
    üdis
    1.39
     começ
    1.38
     desear
    1.37
    ../../
    1.35
     asegur
    1.34
    Activations Density 0.044%

    No Known Activations