© 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. 10-GEMMASCOPE-RES-131K
    7. 60250
    Prev
    Next
    INDEX
    Explanations

    law and justice institutions

    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
     juſt
    -3.08
    小伙伴
    -2.77
    ⸒
    -2.50
    旆
    -2.48
    跸
    -2.47
    tamientos
    -2.47
     vyroben
    -2.44
    嫗
    -2.44
    矢量
    -2.39
     большая
    -2.39
    POSITIVE LOGITS
    Also
    3.48
    In
    3.31
    6
    3.19
    But
    3.14
    ↵
    2.95
    4
    2.91
    On
    2.78
    ９
    2.78
    However
    2.75
    8
    2.75
    Activations Density 0.010%

    No Known Activations