© 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. 22-GEMMASCOPE-RES-131K
    7. 84123
    Prev
    Next
    INDEX
    Explanations

    or conjunction

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

    The neuron is detecting the conjunction “or” (and related disjunctive separators like “/”), signaling alternatives or choices.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     therefore
    -1.00
    ロップ
    -0.95
     wszystkich
    -0.93
    ↑↑
    -0.93
     tamed
    -0.92
    個人的には
    -0.92
    ueuse
    -0.89
     bezw
    -0.89
    අ
    -0.88
    そのため
    -0.87
    POSITIVE LOGITS
    vrier
    1.20
     if
    1.19
     even
    1.13
    だけでも
    1.12
    corrhi
    1.10
     уже
    1.06
     bereits
    1.00
     Even
    0.98
     ask
    0.97
     Sometimes
    0.96
    Activations Density 0.075%

    No Known Activations