© 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. 59328
    Prev
    Next
    INDEX
    Explanations

    fruit and vegetables

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

    The neuron identifies the word "fruit" or "fruits" in text, particularly in contexts related to food, research, or botanical descriptions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ↵
    -3.70
    镦
    -2.78
    紝
    -2.67
    舢
    -2.55
     tokoh
    -2.52
    ઁ
    -2.48
    ed
    -2.45
    or
    -2.42
     ‘’
    -2.36
    ol
    -2.34
    POSITIVE LOGITS
     And
    2.73
    日を
    2.53
     untuk
    2.53
     be
    2.52
     ilumina
    2.45
    翆
    2.42
     και
    2.36
     desnuda
    2.34
     и
    2.33
     cív
    2.31
    Activations Density 0.005%

    No Known Activations