© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3529
    Prev
    Next
    INDEX
    Explanations

    android layout attributes

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

    This neuron fires on programming “attribute” or “parameter” names (e.g. DataType, Orientation, encoding, gravity, Action, Version, etc.) in code.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    際には
    -1.16
    realpath
    -1.13
    際は
    -1.07
    literally
    -1.04
    četně
    -1.03
    
    -1.02
    umption
    -1.02
    赑
    -1.02
    Cuáles
    -1.00
    甃
    -1.00
    POSITIVE LOGITS
     so
    1.02
     }}{\
    0.98
    坩
    0.89
    称号
    0.88
     mansion
    0.86
    iana
    0.84
    IDATE
    0.84
     menceritakan
    0.83
    írito
    0.83
     bestem
    0.83
    Activations Density 0.045%

    No Known Activations