© 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. 34-GEMMASCOPE-RES-131K
    7. 81484
    Prev
    Next
    INDEX
    Explanations

    parsing and converting data

    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_34/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
     DataGridView
    -0.77
     QString
    -0.74
    QString
    -0.73
    gnąć
    -0.72
     LocalDate
    -0.72
     what
    -0.71
    createForm
    -0.71
    驛
    -0.71
    ちゃ
    -0.71
     เด็ก
    -0.70
    POSITIVE LOGITS
     Convert
    3.02
    Convert
    2.77
     Conversion
    1.93
     conversion
    1.90
    Conversion
    1.84
     conversions
    1.79
     Conversions
    1.66
     converts
    1.63
     Converts
    1.63
     convert
    1.63
    Activations Density 0.012%

    No Known Activations