© 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. 69325
    Prev
    Next
    INDEX
    Explanations

    grass and lawns

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

    mentions of grass, lawns, or turf in outdoor settings.

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

    The neuron activates strongly on words referring to grass or lawns.

    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
    middels
    -1.48
    ’,
    -1.33
    ?’
    -1.31
    mouthed
    -1.30
    grained
    -1.26
    ate
    -1.25
    tiness
    -1.24
    𝟔
    -1.23
     —
    -1.22
    BIÉN
    -1.22
    POSITIVE LOGITS
     '
    1.58
     аккура
    1.37
     lawns
    1.30
    ︲
    1.25
    cknow
    1.23
    '
    1.23
     lavorare
    1.23
     buone
    1.20
    Kön
    1.16
     vogliono
    1.13
    Activations Density 0.038%

    No Known Activations