© 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. 14368
    Prev
    Next
    INDEX
    Explanations

    copyright notice in code

    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
    in
    -2.27
    拶
    -1.97
     女優
    -1.94
    。
    -1.94
    s
    -1.89
    born
    -1.87
    ™.
    -1.81
     ferv
    -1.77
    ate
    -1.77
    as
    -1.77
    POSITIVE LOGITS
     atau
    2.05
    iterranée
    2.00
    ⎔
    1.99
    playmobil
    1.91
    除此
    1.89
    であろう
    1.79
    ’,
    1.77
     to
    1.75
    ábado
    1.73
     preferências
    1.72
    Activations Density 0.025%

    No Known Activations