© 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. 22-GEMMASCOPE-RES-131K
    4. 93189
    Prev
    Next
    INDEX
    Explanations

    names of people and organizations

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

    The neuron strongly activates on the standalone, capitalized word “The,” especially when it appears at the start of a headline or document section.

    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
     and
    -1.53
     but
    -1.48
    ãng
    -1.15
     so
    -1.12
     one
    -1.12
    ᐈ
    -1.09
    阿
    -1.09
    ก็
    -1.06
     системой
    -1.06
     all
    -1.05
    POSITIVE LOGITS
    不但
    1.15
     einerseits
    1.15
    логические
    1.15
    NOTAS
    1.14
    大丈夫です
    1.11
    びっくり
    1.08
     alcune
    1.08
    イイ
    1.06
    PÁG
    1.05
    Specifically
    1.04
    Activations Density 0.085%

    No Known Activations