© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63942
    Prev
    Next
    INDEX
    Explanations

    place names and proper nouns starting with "Or"

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

    The neuron specifically fires on the two‐letter token “or” (in either uppercase or lowercase) whenever it appears in the text.

    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
    eton
    -0.80
     otras
    -0.80
    ！（
    -0.79
    primento
    -0.78
     médicas
    -0.77
    最後は
    -0.76
    ربع
    -0.75
    盪
    -0.74
     aplica
    -0.74
     kring
    -0.73
    POSITIVE LOGITS
     Or
    1.13
     Ор
    0.94
     mało
    0.90
    Implementation
    0.84
    Or
    0.84
     Whether
    0.83
    RELATED
    0.81
    𝐥
    0.79
    orate
    0.79
    bayern
    0.78
    Activations Density 0.022%

    No Known Activations