© 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. 10-GEMMASCOPE-RES-131K
    7. 130439
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron fires strongly on specialized names and proper nouns—especially rare technical terms, organization names, and specific titles.

    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
     of
    -1.97
    และ
    -1.58
    ”，
    -1.56
     étoiles
    -1.50
    ”،
    -1.47
    ième
    -1.45
    angkut
    -1.45
    り返
    -1.44
     malgré
    -1.41
     tämän
    -1.38
    POSITIVE LOGITS
     what
    1.94
     how
    1.64
     have
    1.47
     any
    1.38
     completely
    1.31
     conceived
    1.30
    Transcrip
    1.30
    錚
    1.28
     may
    1.27
     characteristics
    1.27
    Activations Density 0.112%

    No Known Activations