© 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. 45608
    Prev
    Next
    INDEX
    Explanations

    sizing options or dietary trans fatty acids

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

    technical syntax patterns in code, database entries, and mathematical notations.

    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
    变换
    -0.76
     coincidence
    -0.75
     search
    -0.72
     Bachelor
    -0.72
    来店
    -0.69
    writeHead
    -0.69
    glo
    -0.69
     impeccable
    -0.67
     dive
    -0.66
     composure
    -0.65
    POSITIVE LOGITS
    nrows
    0.88
     tenues
    0.85
     frutto
    0.84
    toplasmic
    0.81
     recente
    0.80
    ophon
    0.80
     ขนาด
    0.79
    
    0.79
    łym
    0.79
     lanka
    0.78
    Activations Density 0.009%

    No Known Activations