© 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. 43680
    Prev
    Next
    INDEX
    Explanations

    district court

    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
    埽
    -1.68
    贲
    -1.62
    skjaer
    -1.59
     gekomen
    -1.52
     مختلفة
    -1.51
     célula
    -1.48
    âmara
    -1.48
     canaux
    -1.48
    싶
    -1.47
     uitgenodigd
    -1.45
    POSITIVE LOGITS
     to
    1.99
    ).
    1.91
     if
    1.84
    \
    1.84
    ING
    1.81
     for
    1.70
    лося
    1.56
    皤
    1.52
    ท์
    1.52
    _
    1.51
    Activations Density 0.039%

    No Known Activations