© 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. 128796
    Prev
    Next
    INDEX
    Explanations

    making X

    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
    z
    -2.61
    是
    -2.48
    风
    -2.36
     المختلف
    -2.25
     cinese
    -2.25
    徑
    -2.23
     dibujado
    -2.22
    amir
    -2.22
     atau
    -2.20
    最大
    -2.20
    POSITIVE LOGITS
    the
    3.03
    
    2.77
    蠃
    2.70
    葙
    2.66
     employing
    2.58
    摇了
    2.52
    ၜ
    2.52
     making
    2.52
     creando
    2.50
    their
    2.48
    Activations Density 0.027%

    No Known Activations