© 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. 10-GEMMASCOPE-RES-131K
    7. 12256
    Prev
    Next
    INDEX
    Explanations

    opening new windows or tabs

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

    HTML attributes for opening links in new windows or tabs, particularly "target='_blank'" and "window.open".

    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
     cheia
    -1.68
     behöver
    -1.49
     önemli
    -1.40
     réglementation
    -1.37
     to
    -1.34
     eerste
    -1.30
     也
    -1.29
     terá
    -1.26
     tenha
    -1.25
    𓇼
    -1.25
    POSITIVE LOGITS
    6
    2.06
    9
    1.92
    3
    1.88
    0
    1.85
    7
    1.81
    8
    1.77
    most
    1.72
    You
    1.69
    Don
    1.51
    ://
    1.48
    Activations Density 0.004%

    No Known Activations