© 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. 34-GEMMASCOPE-RES-131K
    7. 76771
    Prev
    Next
    INDEX
    Explanations

    first names and surnames

    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_34/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
    ADU
    -0.77
    游戏介绍
    -0.75
     ?></
    -0.72
    浚
    -0.72
     hiz
    -0.71
    ＊＊
    -0.71
     foule
    -0.71
     tund
    -0.69
    ⑧
    -0.69
     hardly
    -0.69
    POSITIVE LOGITS
    ppincott
    0.90
     hegemony
    0.81
     enclosure
    0.78
    immen
    0.78
     mármol
    0.77
    fda
    0.75
    pubs
    0.74
     suun
    0.74
    banden
    0.74
    ennessee
    0.73
    Activations Density 0.020%

    No Known Activations