© 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. 34-GEMMASCOPE-RES-131K
    7. 117439
    Prev
    Next
    INDEX
    Explanations

    county court district

    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_34/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
     armis
    -0.87
     Wolverine
    -0.87
    Wolverine
    -0.85
     MICHIGAN
    -0.84
     cubs
    -0.82
    Michigan
    -0.79
     viad
    -0.79
     Cubs
    -0.79
    Milwaukee
    -0.75
     Audits
    -0.75
    POSITIVE LOGITS
     Forest
    0.84
     forest
    0.84
     Forrest
    0.75
     Friend
    0.75
    chm
    0.73
     Zealand
    0.72
     friend
    0.71
     estrela
    0.70
    udd
    0.69
     alternating
    0.67
    Activations Density 0.064%

    No Known Activations