© 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. 13487
    Prev
    Next
    INDEX
    Explanations

    baked goods and paperclips

    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
    Dữ
    -1.78
     brazen
    -1.73
     dreary
    -1.66
    𖣔
    -1.66
     boneca
    -1.61
     グリル
    -1.59
    桝
    -1.59
     पूरी
    -1.57
    JsonInclude
    -1.56
    膈
    -1.55
    POSITIVE LOGITS
     cotta
    1.93
    𓂅
    1.73
    namientos
    1.59
    一部分
    1.50
     ガーデン
    1.49
    ación
    1.48
    ྃ
    1.48
    的
    1.48
    !”
    1.45
    इटम
    1.45
    Activations Density 0.004%

    No Known Activations