© 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. 65967
    Prev
    Next
    INDEX
    Explanations

    or near/around/about/after/before

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

    The neuron specifically activates on the coordinating conjunction “or.”

    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
     metus
    -0.90
     prêtre
    -0.87
    鳚
    -0.85
    お部屋
    -0.84
     padat
    -0.83
    también
    -0.83
     autres
    -0.82
    Гор
    -0.82
     différents
    -0.81
    immt
    -0.81
    POSITIVE LOGITS
     near
    1.63
     close
    1.25
     slightly
    1.16
    near
    1.15
     nearly
    1.06
     nahezu
    0.96
     Near
    0.93
     próximas
    0.91
     nær
    0.90
     only
    0.88
    Activations Density 0.030%

    No Known Activations