© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100568
    Prev
    Next
    INDEX
    Explanations

    public policy

    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
     -
    -2.34
    ``
    -1.87
     profesores
    -1.63
     días
    -1.63
    มา
    -1.63
     ของ
    -1.63
    มัน
    -1.54
     sons
    -1.51
    ȍ
    -1.50
    ا
    -1.48
    POSITIVE LOGITS
    謦
    1.77
     the
    1.59
     piet
    1.48
     ducato
    1.47
    鱘
    1.45
     boya
    1.44
     roulant
    1.43
    鋌
    1.41
     prate
    1.41
    いろんな
    1.41
    Activations Density 0.011%

    No Known Activations