© 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. 41898
    Prev
    Next
    INDEX
    Explanations

    song dynasty, pacific island, swiss

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

    The neuron fires on subword pieces of proper names and specialized terms—i.e. parts of named entities like personal names, place names, or disease 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_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
     those
    -1.92
     both
    -1.62
     your
    -1.58
     you
    -1.46
     ceux
    -1.43
     our
    -1.42
    ara
    -1.39
    ～。
    -1.38
     these
    -1.34
    uti
    -1.34
    POSITIVE LOGITS
    𐤔
    1.55
    nintendo
    1.48
    babwe
    1.45
    髭
    1.42
    uol
    1.39
    zerű
    1.38
    tvguide
    1.38
    cardigan
    1.37
    Sqft
    1.36
     '-',
    1.36
    Activations Density 1.124%

    No Known Activations