© 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. 59835
    Prev
    Next
    INDEX
    Explanations

    perfectly fine

    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
     rất
    -1.16
     дуже
    -1.11
     очень
    -1.10
     very
    -1.10
     très
    -1.07
     velmi
    -1.05
     veľmi
    -1.02
     labai
    -1.02
     bardzo
    -0.96
    ierter
    -0.95
    POSITIVE LOGITS
     accurate
    1.67
     strong
    1.64
     steep
    1.48
     expensive
    1.43
     good
    1.38
     large
    1.37
     important
    1.33
     tall
    1.28
     easy
    1.24
     loud
    1.23
    Activations Density 0.068%

    No Known Activations