© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101790
    Prev
    Next
    INDEX
    Explanations

    fruits

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

    The neuron activates for the word "fruits" in the context of food and agriculture.

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

    The neuron specifically detects occurrences of the plural noun “fruits.”

    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
    ↵
    -2.78
    ,”
    -2.45
     ”
    -2.41
    ”
    -2.39
    ),
    -2.30
    *
    -2.28
    ”,
    -2.19
    ie
    -2.16
    \"
    -2.14
    or
    -2.13
    POSITIVE LOGITS
     fruits
    2.92
    vantaged
    2.72
     entirety
    2.48
    衚
    2.36
    ᭡
    2.27
    🕗
    2.20
    kipun
    2.13
    𓆜
    2.13
    筆記
    2.11
     hän
    2.05
    Activations Density 0.002%

    No Known Activations