© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209896
    Prev
    Next
    INDEX
    Explanations

    preparations for introduction

    np_acts-logits-general · gemini-2.5-flash-lite

    tests questions and resource usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的分
    0.47
    ซ์
    0.46
    يد
    0.45
     hela
    0.44
    }[(
    0.44
    斯
    0.43
    なら
    0.43
     average
    0.43
    斯拉
    0.42
    哀
    0.42
    POSITIVE LOGITS
     diversión
    0.52
     señala
    0.52
     preparação
    0.52
    descricao
    0.50
     petición
    0.49
     composição
    0.49
     несо
    0.48
     insuf
    0.47
     précieux
    0.47
     дополнительных
    0.47
    Activations Density 0.001%

    No Known Activations