© 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. 34-GEMMASCOPE-RES-131K
    7. 58550
    Prev
    Next
    INDEX
    Explanations

    Q: or Rituximab or Dobot

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

    Android XML layout elements, particularly ImageView components and their attributes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric literals (sequences of digits) embedded in the code or XML.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     السب
    -0.87
    字体
    -0.77
     getText
    -0.73
     Text
    -0.73
     text
    -0.72
     Spire
    -0.72
    enciais
    -0.71
     STRUCT
    -0.71
    ʜ
    -0.70
     TEXT
    -0.70
    POSITIVE LOGITS
    src
    1.16
     src
    1.12
    setImageResource
    1.00
     setImage
    1.00
     source
    0.94
    scale
    0.92
     SOURCE
    0.92
     sources
    0.91
    source
    0.88
     scale
    0.88
    Activations Density 0.006%

    No Known Activations