© 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. 40352
    Prev
    Next
    INDEX
    Explanations

    our + collective nouns

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

    This neuron detects single-word, capitalized section or menu headings (standalone title labels) in the 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_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
     fermée
    -1.27
     his
    -1.24
     grecque
    -1.23
     couverte
    -1.21
    多かった
    -1.20
     手順
    -1.20
     heut
    -1.20
    絎
    -1.20
     himself
    -1.19
    ほとん
    -1.17
    POSITIVE LOGITS
     our
    2.23
     ourselves
    1.63
    Our
    1.61
     and
    1.34
     μας
    1.24
     nostra
    1.20
     unseren
    1.20
    ＂
    1.18
     we
    1.10
    !」
    1.09
    Activations Density 0.071%

    No Known Activations