© 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. 10-GEMMASCOPE-RES-131K
    7. 73765
    Prev
    Next
    INDEX
    Explanations

    linking items with plus

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

    This neuron detects the plus‐sign character (“+”), especially when used to join or highlight terms in headings and section titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     it
    -2.14
     serían
    -1.90
     to
    -1.84
     you
    -1.73
     mencegah
    -1.71
     seguirá
    -1.67
     During
    -1.67
     or
    -1.66
    なのですが
    -1.64
     Hopefully
    -1.63
    POSITIVE LOGITS
    ☫
    2.20
    ⬯
    2.03
    帮你
    1.98
     ส์
    1.98
    臯
    1.85
    蹿
    1.81
     rumored
    1.80
    ୬
    1.79
    ᷆
    1.78
    媃
    1.78
    Activations Density 0.023%

    No Known Activations