© 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. 39630
    Prev
    Next
    INDEX
    Explanations

    dual options

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

    The neuron strongly responds to occurrences of the word “both” when it’s used to link or list two items or categories.

    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
    などを
    -1.15
     dwóch
    -1.13
    もある
    -1.13
    ins
    -1.12
    two
    -1.09
    ust
    -1.08
    を
    -1.06
    见状
    -1.05
     cliquant
    -1.05
    oczes
    -1.05
    POSITIVE LOGITS
    Both
    1.25
    気がします
    1.07
    แบบ
    1.07
     both
    1.05
    為に
    1.04
    agisse
    1.02
    ほうがいい
    0.97
    お気軽
    0.97
    Fiction
    0.95
    Inspiration
    0.94
    Activations Density 0.076%

    No Known Activations