© 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. 130488
    Prev
    Next
    INDEX
    Explanations

    growers and anglers

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

    This neuron detects occurrences of the root “grow” (e.g. grow, growers, grower) 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_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
    }
    -3.63
    1
    -2.84
    n
    -2.67
    3
    -2.63
    2
    -2.59
    ”
    -2.59
    os
    -2.36
    Z
    -2.23
    那個
    -2.20
     '
    -2.19
    POSITIVE LOGITS
     of
    2.69
    嵛
    2.61
    嗞
    2.50
    鹮
    2.45
    ℟
    2.41
    
    2.36
     パッド
    2.33
     uſed
    2.31
     núm
    2.31
    ’，
    2.28
    Activations Density 0.002%

    No Known Activations