© 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. 25580
    Prev
    Next
    INDEX
    Explanations

    total, mass, volume

    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
     three
    -0.83
     five
    -0.80
     Métro
    -0.76
     eight
    -0.75
    ၢ
    -0.70
     siswa
    -0.69
    São
    -0.68
     four
    -0.67
    ције
    -0.66
     six
    -0.66
    POSITIVE LOGITS
     total
    1.10
     totale
    0.91
     कुल
    0.90
     مجموع
    0.88
    totalAmount
    0.87
     общий
    0.87
     estoque
    0.86
     revenue
    0.85
    total
    0.85
    مجموع
    0.84
    Activations Density 0.056%

    No Known Activations