© 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. 22-GEMMASCOPE-RES-131K
    7. 26720
    Prev
    Next
    INDEX
    Explanations

    reading and studying

    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_22/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
    ссовки
    -1.01
    ᧐
    -1.00
    ダース
    -1.00
    量の
    -0.99
     Хар
    -0.98
     society
    -0.98
    创意
    -0.93
     الفلك
    -0.93
     soothe
    -0.92
    袄
    -0.92
    POSITIVE LOGITS
     read
    1.26
     reading
    1.23
    髂
    1.23
     liné
    1.18
    licopter
    1.17
     bogor
    1.13
    ktı
    1.10
    因为它
    1.09
     okuyayım
    1.06
     đọc
    1.05
    Activations Density 0.041%

    No Known Activations