© 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. 85003
    Prev
    Next
    INDEX
    Explanations

    code context punctuation

    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
     But
    -1.80
     it
    -1.48
    着一个
    -1.45
     unimaginable
    -1.41
     Gegensatz
    -1.41
     ingrained
    -1.38
     Hinblick
    -1.38
     soothing
    -1.36
    仪式
    -1.35
     verfolgt
    -1.35
    POSITIVE LOGITS
    sizeCache
    1.51
    ૯
    1.48
    怎样
    1.45
    ೢ
    1.39
    requestCode
    1.39
    gleichen
    1.36
    :=\
    1.36
    \}$.
    1.33
    )},
    1.31
     pasien
    1.30
    Activations Density 0.006%

    No Known Activations