© 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. 11239
    Prev
    Next
    INDEX
    Explanations

    period or periodon-

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

    references to time periods or durations.

    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
     incredibly
    -2.50
     THERE
    -2.47
    瀦
    -2.42
     unreasonably
    -2.31
     permanecer
    -2.31
     unveils
    -2.25
     utilisé
    -2.23
     gestartet
    -2.22
     vielleicht
    -2.16
    あります
    -2.14
    POSITIVE LOGITS
    鴣
    3.09
    銩
    2.56
    ↑↑↑</
    2.56
    १
    2.48
     igenom
    2.36
    ஂ
    2.33
    乆
    2.25
     "";
    2.25
    🌟
    2.22
    ～！
    2.20
    Activations Density 0.019%

    No Known Activations