© 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. 127235
    Prev
    Next
    INDEX
    Explanations

    F.Supp. citations

    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
    ':
    -1.49
    ۱
    -1.45
    妖精
    -1.43
    },
    -1.41
     cuando
    -1.40
    適量
    -1.35
     православ
    -1.35
    &
    -1.34
    。“
    -1.34
    %',
    -1.34
    POSITIVE LOGITS
    今も
    1.50
    ごとの
    1.42
     where
    1.40
     determinada
    1.34
    だら
    1.31
    コク
    1.30
     apariencia
    1.29
    呶
    1.29
     funcionam
    1.29
     мамы
    1.28
    Activations Density 0.069%

    No Known Activations