© 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. 13186
    Prev
    Next
    INDEX
    Explanations

    that / which followed by a verb

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

    The neuron strongly activates on the word “that.”

    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
    ных
    -1.18
     также
    -1.17
    grimas
    -1.16
     Gambar
    -1.08
     offering
    -1.08
    ྱ
    -1.06
    因为它
    -1.06
     piscina
    -1.05
     autentic
    -1.04
     formule
    -1.03
    POSITIVE LOGITS
     others
    1.34
     commensurate
    1.07
     wuß
    1.06
     līdz
    1.04
     соотно
    1.02
     Schuhe
    1.00
     unimaginable
    1.00
     gewöhn
    0.98
     suited
    0.98
     glaub
    0.97
    Activations Density 0.047%

    No Known Activations