© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102529
    Prev
    Next
    INDEX
    Explanations

    media screen and

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

    This neuron detects CSS media‐query conditions (e.g. “screen and (min-width…)” or “screen and (max-width…)”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     the
    -1.74
     促销
    -1.71
    粜
    -1.70
    땃
    -1.70
     商店
    -1.67
    schwar
    -1.63
     estadounid
    -1.60
    笵
    -1.59
    箧
    -1.54
    ⃢
    -1.54
    POSITIVE LOGITS
    ↵↵
    1.67
     (
    1.55
    Aunque
    1.48
    ・
    1.43
    for
    1.39
    There
    1.38
    に
    1.38
     };
    
    1.33
    籁
    1.31
     pentru
    1.30
    Activations Density 0.003%

    No Known Activations