© 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. 34-GEMMASCOPE-RES-131K
    7. 63344
    Prev
    Next
    INDEX
    Explanations

    numbers with fractions

    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_34/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
     two
    -1.08
    สอง
    -1.05
    二
    -0.97
     två
    -0.95
     două
    -0.91
    Zwei
    -0.91
     δύο
    -0.90
     kaksi
    -0.87
     azo
    -0.85
    deux
    -0.84
    POSITIVE LOGITS
    3
    1.23
     third
    1.00
     three
    0.92
     trzec
    0.90
    ３
    0.89
    ۳
    0.85
     dritten
    0.84
     третий
    0.82
     трех
    0.82
     ketiga
    0.82
    Activations Density 0.061%

    No Known Activations