© 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. 10634
    Prev
    Next
    INDEX
    Explanations

    county court or civil 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
     about
    -1.67
     místa
    -1.51
    perhaps
    -1.51
    にゃ
    -1.50
    ねえ
    -1.48
     Теперь
    -1.47
    ってました
    -1.46
     espaços
    -1.45
     汽車
    -1.44
     Streifen
    -1.42
    POSITIVE LOGITS
     COUNTY
    1.67
     участок
    1.63
    良好的
    1.59
     hvert
    1.56
     will
    1.52
    朦
    1.48
    replyreport
    1.46
    蛧
    1.45
     it
    1.44
     ricord
    1.42
    Activations Density 0.065%

    No Known Activations