© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99585
    Prev
    Next
    INDEX
    Explanations

    Taq, Iqaluit, Tacoma, Tacloban

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

    The neuron chiefly activates on tokens containing the letter “q.”

    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
     unless
    -0.87
    unless
    -0.84
    Unless
    -0.80
     Unless
    -0.76
    璇
    -0.76
    ýl
    -0.75
    Homme
    -0.75
     třeba
    -0.75
     Baños
    -0.74
    յ
    -0.74
    POSITIVE LOGITS
    تق
    1.02
     تق
    0.94
    תק
    0.76
    loro
    0.75
     imitation
    0.73
     unsettled
    0.67
     Colleagues
    0.67
     התק
    0.66
     permintaan
    0.65
     techni
    0.64
    Activations Density 0.006%

    No Known Activations