© 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. 90668
    Prev
    Next
    INDEX
    Explanations

    millet, sorghum, myeloma

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

    The neuron activates on mentions of cereal grains or related crop species (e.g., millet, sorghum, barnyard millet, Coix).

    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
     夜景
    -2.38
    ドキ
    -2.34
     všem
    -2.31
    滎
    -2.27
    賒
    -2.25
    渽
    -2.22
    欉
    -2.14
    肫
    -2.13
    푡
    -2.11
    髡
    -2.11
    POSITIVE LOGITS
    )
    3.28
    “
    2.91
    玊
    2.58
    6
    2.52
    </i>
    2.41
     เมื่อ
    2.34
     Когда
    2.23
    ),
    2.17
     When
    2.13
    та
    2.02
    Activations Density 0.004%

    No Known Activations