© 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. 22-GEMMASCOPE-RES-131K
    7. 84419
    Prev
    Next
    INDEX
    Explanations

    IU, lact, substituted, time, symptoms

    np_acts-logits-general · gemini-2.5-flash-lite

    brackets, punctuation marks, and other text formatting elements in technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    citroen
    -0.97
     subsequently
    -0.96
     possibly
    -0.96
    [][
    -0.95
     almost
    -0.93
     eventual
    -0.92
     many
    -0.92
     potentially
    -0.91
     Michael
    -0.88
     initially
    -0.87
    POSITIVE LOGITS
     beter
    0.97
     militer
    0.96
     vernac
    0.94
     ſec
    0.92
    despite
    0.92
     milla
    0.91
    たまに
    0.90
     bross
    0.90
    なんとなく
    0.90
    provide
    0.89
    Activations Density 0.071%

    No Known Activations