© 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. 23710
    Prev
    Next
    INDEX
    Explanations

    acute attacks

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

    legal citation patterns, particularly in court cases where one party is versus ("v.") another.

    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_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
     Emil
    -0.66
     counsel
    -0.65
     early
    -0.65
     библиоте
    -0.61
     Taylor
    -0.61
    机构
    -0.60
    noli
    -0.60
     Sarah
    -0.60
    сторо
    -0.60
     monarchs
    -0.60
    POSITIVE LOGITS
     Medvedev
    0.77
     lefs
    0.74
     Principle
    0.73
    朝着
    0.72
     alcun
    0.70
     جواب
    0.69
    inev
    0.68
     项目
    0.68
     slat
    0.68
     Cranston
    0.68
    Activations Density 0.076%

    No Known Activations