© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123572
    Prev
    Next
    INDEX
    Explanations

    relative pronoun introducing clauses

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

    The neuron fires most strongly on a noun that heads a “that” relative clause (e.g. the “clutches” in “clutches that are typical,” “vulnerability” in “vulnerability that made,” “folding” in “folding that affected,” etc.).

    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
     such
    -1.55
     був
    -1.47
    Different
    -1.42
    "},
    
    -1.38
    Koordinaten
    -1.36
    大さじ
    -1.34
    numerus
    -1.34
     ネタバレ
    -1.33
    entuh
    -1.30
    一群
    -1.29
    POSITIVE LOGITS
     we
    2.02
     of
    1.65
     aucune
    1.65
    够了
    1.65
     they
    1.61
    GIUM
    1.55
     podríamos
    1.52
    谖
    1.51
    for
    1.48
     atualmente
    1.43
    Activations Density 0.050%

    No Known Activations