© 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. 93446
    Prev
    Next
    INDEX
    Explanations

    fruits and orchards

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

    XML-like syntax or text with formatting patterns, particularly with angle brackets and structured content.

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

    The neuron is specialized to pick out XML/HTML tag markup (angle brackets and tag names).

    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
    大豆
    -1.20
     arroz
    -1.08
    花生
    -1.05
     oregano
    -0.99
     peppermint
    -0.97
     rosemary
    -0.97
    Chicken
    -0.96
     капу
    -0.95
     canola
    -0.94
     bison
    -0.93
    POSITIVE LOGITS
     fruit
    3.52
     Fruit
    2.61
    Fruit
    2.59
    fruit
    2.56
     fruits
    2.45
     FRUIT
    2.20
     fruity
    2.06
     orchard
    2.03
     Fruits
    1.97
     orchards
    1.90
    Activations Density 0.103%

    No Known Activations