© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101085
    Prev
    Next
    INDEX
    Explanations

    this followed by a specific noun

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

    The neuron consistently fires on the demonstrative "this" in running 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_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
     acoged
    -1.62
     使っ
    -1.54
     camiones
    -1.52
     farmacé
    -1.48
     acogedor
    -1.47
     másik
    -1.45
     destiné
    -1.44
     part
    -1.43
     berbeda
    -1.41
     will
    -1.39
    POSITIVE LOGITS
    ⦊
    1.41
     condol
    1.38
     exacerb
    1.38
    Leírás
    1.36
     incess
    1.35
     promulg
    1.33
     inconce
    1.32
     nause
    1.31
     debilit
    1.30
     Oft
    1.29
    Activations Density 0.112%

    No Known Activations