© 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. 22406
    Prev
    Next
    INDEX
    Explanations

    step followed by number or symbol

    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
    但是在
    -2.58
    '__
    -2.39
     halbe
    -2.36
     gustaMe
    -2.36
    頷
    -2.28
    倂
    -2.23
     débris
    -2.20
     ,‬
    -2.17
    但在
    -2.13
     to
    -2.11
    POSITIVE LOGITS
     financière
    3.19
    Now
    3.19
    The
    3.17
     éditoriale
    3.17
    
    2.97
    If
    2.88
     Для
    2.78
     intellectuelle
    2.75
    最後の
    2.69
    You
    2.67
    Activations Density 0.012%

    No Known Activations