© 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. 22-GEMMASCOPE-RES-131K
    7. 68655
    Prev
    Next
    INDEX
    Explanations

    bamboo, hemp, cane, asbestos, beads

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

    This neuron detects mentions of bamboo (including species names and extracts) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    􀂃
    -2.70
    }
    -2.66
    焌
    -2.58
    ar
    -2.48
    他
    -2.48
    il
    -2.47
    肫
    -2.44
    元的
    -2.41
    ☫
    -2.39
    
    -2.36
    POSITIVE LOGITS
    獁
    2.55
    はじめ
    2.47
    𓆜
    2.42
    亊
    2.39
    此事
    2.33
    翫
    2.30
     Which
    2.30
     Any
    2.28
    鬭
    2.28
    which
    2.23
    Activations Density 0.012%

    No Known Activations