© 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. 129932
    Prev
    Next
    INDEX
    Explanations

    protests and revolts

    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
     pouvaient
    -1.25
    ન્
    -1.20
    ).
    -1.19
     двигатель
    -1.18
    قة
    -1.16
     biologie
    -1.15
    也不知道
    -1.11
     նաև
    -1.11
     possible
    -1.06
     точку
    -1.06
    POSITIVE LOGITS
     have
    1.43
     four
    1.38
     three
    1.36
     it
    1.35
    毉
    1.29
    絎
    1.29
     five
    1.27
     ہیں۔
    1.27
     dotyczące
    1.27
     eight
    1.23
    Activations Density 0.068%

    No Known Activations