© 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. 59164
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
    '
    -1.20
     abbiano
    -1.06
     particolare
    -1.06
    因为它
    -1.06
     Celebr
    -1.06
    说出
    -1.05
     same
    -1.03
    CARACTERIST
    -1.03
    躥
    -1.00
     possibilidade
    -0.99
    POSITIVE LOGITS
    mặt
    1.23
    ään
    1.19
    Ῥ
    1.16
    Daha
    1.14
     будут
    1.11
    عرض
    1.10
    大切な
    1.09
    ྄
    1.07
    hộp
    1.07
    Zobacz
    1.06
    Activations Density 0.055%

    No Known Activations