© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109748
    Prev
    Next
    INDEX
    Explanations

    riboflavin, sclerotherapy

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

    scientific or technical terminology in academic papers and articles.

    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
     what
    -0.96
    kā
    -0.95
     Гри
    -0.92
     these
    -0.91
    inhas
    -0.89
    的基础
    -0.88
     furthermore
    -0.88
     favorece
    -0.87
     you
    -0.86
     there
    -0.85
    POSITIVE LOGITS
     $^{\
    1.23
     войск
    1.13
     gummy
    1.13
    Pets
    1.11
     ${\
    1.05
     Dinas
    1.04
     }}{
    1.02
    
    1.02
    </h4>
    1.02
    Extremely
    0.98
    Activations Density 0.348%

    No Known Activations