© 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. 58664
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific formulas

    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
    𞤢
    -2.86
    
    -2.80
    𞤤
    -2.77
    蒾
    -2.50
    鐿
    -2.47
     unſ
    -2.41
    赑
    -2.23
     стоковые
    -2.22
    躂
    -2.22
    jaqueta
    -2.16
    POSITIVE LOGITS
    !”
    2.67
    a
    2.47
    .”
    2.45
    .
    2.38
    x
    2.34
    to
    2.31
    re
    2.28
    ”
    2.20
    er
    2.20
    ?”
    2.11
    Activations Density 0.015%

    No Known Activations