© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91176
    Prev
    Next
    INDEX
    Explanations

    wild

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

    The neuron primarily detects occurrences of the word “wild” (in any case) as part of names or titles.

    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
     dentista
    -0.80
    purch
    -0.77
     física
    -0.77
     maria
    -0.75
     rédaction
    -0.75
    いらっしゃ
    -0.72
     noce
    -0.71
     prochaine
    -0.70
     Poids
    -0.69
    校长
    -0.68
    POSITIVE LOGITS
     wild
    1.69
     Wild
    1.62
    Wild
    1.51
    wild
    1.45
    cards
    1.44
     west
    1.22
    carded
    1.15
     WILD
    1.13
    cat
    1.13
    flower
    1.13
    Activations Density 0.012%

    No Known Activations