© 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. 64879
    Prev
    Next
    INDEX
    Explanations

    Op-Ed, opioid, opiate

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

    The neuron is a sub‐word detector that fires strongly on the two‐letter sequence “op” (e.g. in “Op-Ed,” “opioid,” names like “Op De …”).

    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
     Touring
    -0.82
     Evolutionary
    -0.81
     touring
    -0.80
    bn
    -0.77
    yakit
    -0.75
    铬
    -0.75
     Cody
    -0.74
    Executor
    -0.74
     Bah
    -0.74
     Simone
    -0.73
    POSITIVE LOGITS
     room
    0.71
    SqlConnection
    0.70
    どうしても
    0.68
    ihin
    0.66
    pricht
    0.63
    စ
    0.63
    corporated
    0.63
     Gap
    0.62
     nossa
    0.61
    価格は
    0.61
    Activations Density 0.074%

    No Known Activations