© 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. 86863
    Prev
    Next
    INDEX
    Explanations

    wear and its common suffixes

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

    The neuron detects occurrences of the substring “wear” within words (e.g., wear, wearer, wearables, Wear).

    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
    katapos
    -0.87
    致します
    -0.81
    するために
    -0.80
     perut
    -0.80
    {§
    -0.79
    terms
    -0.79
     fumar
    -0.78
    メス
    -0.78
    Cakes
    -0.78
     أحمد
    -0.77
    POSITIVE LOGITS
    ables
    1.63
    isome
    1.28
    able
    1.00
    cep
    0.92
    ABLES
    0.90
     Wear
    0.89
    ableView
    0.88
    Tear
    0.85
     ağır
    0.84
     estavam
    0.83
    Activations Density 0.009%

    No Known Activations