© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100611
    Prev
    Next
    INDEX
    Explanations

    script src attribute

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

    the `src` attribute in HTML script and link tags.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.98
    At
    -1.88
    For
    -1.67
    When
    -1.54
    All
    -1.52
     if
    -1.51
    According
    -1.48
    というと
    -1.48
    _
    -1.45
    Because
    -1.44
    POSITIVE LOGITS
     the
    1.71
     黄色
    1.66
    逦
    1.59
     here
    1.59
     kuv
    1.58
     流れ
    1.56
    
    1.56
    嫋
    1.56
    苳
    1.53
    蘧
    1.52
    Activations Density 0.059%

    No Known Activations