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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 74730
    Prev
    Next
    INDEX
    Explanations

    anabolic steroids or LibreOffice

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

    noun sequences that form specialized terminology, particularly in fields like computing, chemistry, and medicine.

    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_10/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
    甗
    -1.84
    
    -1.65
     некоторых
    -1.63
    瘣
    -1.63
     válida
    -1.59
     mohou
    -1.53
    )=>{
    
    -1.52
    
    -1.51
    ՚
    -1.51
     ‘’
    -1.51
    POSITIVE LOGITS
     but
    1.83
     or
    1.78
     When
    1.70
     for
    1.66
     at
    1.57
    ischof
    1.47
     he
    1.44
     time
    1.42
     so
    1.41
     still
    1.41
    Activations Density 0.034%

    No Known Activations