© 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. 89809
    Prev
    Next
    INDEX
    Explanations

    engraving, drawings, prints

    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
    のことを
    -0.96
     για
    -0.88
     измене
    -0.84
     логоти
    -0.82
     fanfiction
    -0.79
     écrire
    -0.79
    uskan
    -0.77
     Neon
    -0.75
     geschrieben
    -0.75
     feedback
    -0.73
    POSITIVE LOGITS
     engraving
    1.61
     illustrations
    1.51
     engravings
    1.50
     prints
    1.43
     lith
    1.33
     drawings
    1.30
    挿
    1.26
     print
    1.24
     illustration
    1.23
     illustrated
    1.22
    Activations Density 0.043%

    No Known Activations