© 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. 20291
    Prev
    Next
    INDEX
    Explanations

    words containing wood

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

    The neuron detects occurrences of the substring “wood” inside words.

    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
    歘
    -3.13
     vostra
    -2.78
    蚍
    -2.64
    ᠂
    -2.59
    釙
    -2.55
     nahil
    -2.53
    筇
    -2.53
    鼉
    -2.52
     sabbia
    -2.50
    旂
    -2.50
    POSITIVE LOGITS
    趼
    4.19
     für
    3.69
    𓆜
    3.13
    媄
    3.00
    ––
    2.98
    wood
    2.94
    鈊
    2.91
    _
    2.88
     of
    2.86
    苼
    2.83
    Activations Density 0.005%

    No Known Activations