© 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. 35911
    Prev
    Next
    INDEX
    Explanations

    these, this, amount, three

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

    This neuron fires on the copular “is/that” constructions in declarative explanation or definition sentences—e.g. phrases like “is that the script runs…” or “The present invention…”

    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
     Chất
    -0.88
     там
    -0.85
     reducir
    -0.84
    ֱ
    -0.81
     slika
    -0.80
     biopsies
    -0.78
    .*;
    -0.78
     đã
    -0.77
     lạt
    -0.76
     berikut
    -0.75
    POSITIVE LOGITS
     these
    1.73
     queste
    1.36
    这些
    1.32
    these
    1.26
    這些
    1.22
    These
    1.17
     These
    1.11
    これらの
    1.10
     Queste
    1.05
     this
    1.05
    Activations Density 0.096%

    No Known Activations