© 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. 84722
    Prev
    Next
    INDEX
    Explanations

    positive and descriptive adjectives

    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
    较高
    -1.09
     it
    -1.03
     ouvrage
    -1.00
    ditionally
    -0.98
     مختلفة
    -0.97
    浓郁
    -0.97
    常见的
    -0.95
     плохо
    -0.94
     uitgenodigd
    -0.93
     añade
    -0.90
    POSITIVE LOGITS
     wonderful
    4.72
     fantastic
    4.03
     amazing
    3.77
     excellent
    3.73
     awesome
    3.61
     terrific
    3.52
     fabulous
    3.36
     lovely
    3.30
    wonderful
    3.16
     superb
    3.08
    Activations Density 0.221%

    No Known Activations