© 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. 34-GEMMASCOPE-RES-131K
    7. 564
    Prev
    Next
    INDEX
    Explanations

    hay and related words

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

    The neuron strongly activates on terms related to hay bales and hay‐baling equipment.

    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
    Akan
    -0.86
     Shells
    -0.80
    Blur
    -0.76
     рис
    -0.76
    drawSprites
    -0.75
    եց
    -0.73
    춰
    -0.73
    ismuth
    -0.73
    iped
    -0.73
    blues
    -0.71
    POSITIVE LOGITS
     hay
    2.30
    Hay
    2.03
     Hay
    1.93
     bales
    1.88
    hay
    1.77
     bale
    1.76
     HAY
    1.71
    HAY
    1.59
     bal
    1.52
     haystack
    1.39
    Activations Density 0.022%

    No Known Activations