© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7987
    Prev
    Next
    INDEX
    Explanations

    rem comments and em units

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

    This neuron detects CSS length values (particularly those using the “rem” unit) in style declarations.

    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
     it
    -1.82
     thing
    -1.80
     reputación
    -1.75
     well
    -1.73
    のだが
    -1.70
    :}
    -1.68
    ၉
    -1.67
     también
    -1.66
    倨
    -1.64
     think
    -1.63
    POSITIVE LOGITS
    I
    2.16
    йся
    1.77
    ка
    1.77
    The
    1.77
    етесь
    1.70
    Their
    1.70
    ток
    1.66
    в
    1.65
    怱
    1.63
     rapat
    1.61
    Activations Density 0.001%

    No Known Activations