© 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. 7336
    Prev
    Next
    INDEX
    Explanations

    young adult and adult age

    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
    持續
    -1.66
    诞生
    -1.62
    是個
    -1.60
    戰爭
    -1.60
    かげ
    -1.59
    鯰
    -1.57
    ћа
    -1.54
    攢
    -1.54
     brevemente
    -1.54
     celebrated
    -1.52
    POSITIVE LOGITS
     of
    2.22
    “
    1.71
    eapples
    1.64
    %,
    1.63
    上官
    1.59
    烙
    1.56
    section
    1.48
     Highly
    1.48
    也能
    1.46
    '].'
    1.46
    Activations Density 0.010%

    No Known Activations