© 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. 22-GEMMASCOPE-RES-131K
    7. 66105
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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_22/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
     correcte
    -0.97
     équipée
    -0.93
    wasn
    -0.92
    didn
    -0.91
    couldn
    -0.91
     neuve
    -0.90
     dansk
    -0.89
     MUNDO
    -0.89
    wouldn
    -0.89
    berater
    -0.87
    POSITIVE LOGITS
     are
    1.05
     provide
    0.99
     allows
    0.98
     between
    0.96
    lanniksi
    0.94
     produces
    0.93
     enables
    0.93
     provides
    0.90
     combines
    0.88
     during
    0.87
    Activations Density 0.057%

    No Known Activations