© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75672
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Hinsicht
    -2.48
     ketika
    -2.45
    the
    -2.45
     henceforth
    -2.42
    It
    -2.33
    -
    -2.31
    سبة
    -2.23
    最適
    -2.23
     For
    -2.16
    亟
    -2.16
    POSITIVE LOGITS
    其妙
    3.70
    ⧼
    3.16
    煳
    3.02
    臜
    2.97
     ſont
    2.94
    茘
    2.94
    wiście
    2.84
    ⵌ
    2.83
    鲵
    2.83
    følgelig
    2.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.