© 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. 40062
    Prev
    Next
    INDEX
    Explanations

    definition or description

    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
     如
    -1.44
     namen
    -1.28
    heres
    -1.22
    ”、“
    -1.19
    ORATION
    -1.19
    張り
    -1.18
    籴
    -1.18
     principalement
    -1.18
     treu
    -1.16
     得
    -1.14
    POSITIVE LOGITS
     này
    1.65
     también
    1.47
    에서는
    1.36
     Waktu
    1.36
     biçim
    1.34
     ısı
    1.33
     these
    1.31
    volante
    1.29
     çerçe
    1.28
     Further
    1.27
    Activations Density 0.029%

    No Known Activations