© 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. 34-GEMMASCOPE-RES-131K
    7. 733
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

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

    This neuron fires on named identifiers—tokens that are part of proper names or technical identifiers (e.g. code import paths and personal names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    の高
    -0.77
     Mantle
    -0.74
    닐
    -0.73
     испыты
    -0.71
    Часть
    -0.71
     وسایل
    -0.71
     autocollant
    -0.71
    örung
    -0.71
    hren
    -0.70
     memang
    -0.70
    POSITIVE LOGITS
     agric
    0.74
    يره
    0.71
    знес
    0.70
    naam
    0.69
    Lage
    0.69
    /'.$
    0.68
    ꞉
    0.68
     SizedBox
    0.67
     następu
    0.67
     เด
    0.66
    Activations Density 0.019%

    No Known Activations