© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113993
    Prev
    Next
    INDEX
    Explanations

    UI code elements and Objective-C classes

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

    the word "GridView" or "NSObject" in programming code contexts.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    Negative Logits
    豨
    -2.67
    蜴
    -2.56
     TÉCNICA
    -2.50
    ፨
    -2.45
     boletín
    -2.41
    眉毛
    -2.39
    möglichen
    -2.36
    ."
    -2.36
    
    -2.31
    
    -2.31
    POSITIVE LOGITS
    n
    3.63
     “
    3.45
    .
    2.66
    ,
    2.64
    '
    2.55
    an
    2.50
    寕
    2.42
    {
    2.27
     мои
    2.22
    <sup>
    2.16
    Activations Density 0.003%

    No Known Activations