© 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. 84101
    Prev
    Next
    INDEX
    Explanations

    tomatoes and potatoes

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

    food items, particularly tomatoes and potatoes.

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

    The neuron strongly activates on occurrences of “tomato” or “tomatoes” in the text.

    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
    a
    -3.67
    ed
    -3.31
    z
    -3.23
    an
    -3.16
    re
    -3.16
    er
    -3.11
    e
    -2.98
    n
    -2.73
    us
    -2.63
    ا
    -2.59
    POSITIVE LOGITS
     แต่
    3.05
    鮰
    2.98
    vantaged
    2.69
    ↵
    2.69
    ܊
    2.64
    ᡵ
    2.59
    岽
    2.59
    髏
    2.59
    鹮
    2.56
    狴
    2.47
    Activations Density 0.005%

    No Known Activations