© 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. 103146
    Prev
    Next
    INDEX
    Explanations

    media queries and screen

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

    CSS media query syntax in HTML and code, particularly the `media` attribute and query expressions.

    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
    。”
    -1.59
     have
    -1.53
    ’).
    -1.45
    "));
    -1.45
    ka
    -1.45
     of
    -1.40
    ☹
    -1.38
    s
    -1.37
    😒
    -1.36
    😝
    -1.36
    POSITIVE LOGITS
    つづく
    1.38
    就是这样
    1.31
     geschützt
    1.30
     μπορεί
    1.30
     člověk
    1.27
     liebt
    1.26
     bulunabilir
    1.25
     heighten
    1.24
    ~ 
    1.24
    関連記事
    1.23
    Activations Density 0.018%

    No Known Activations