© 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. 90814
    Prev
    Next
    INDEX
    Explanations

    names and days of week

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

    This neuron primarily picks up parenthetical numeric references (numbers and related tokens inside parentheses).

    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
     имеет
    -1.48
     Если
    -1.44
     gnar
    -1.42
     véhic
    -1.40
    ladung
    -1.40
    责编
    -1.38
     détect
    -1.37
    </h6>
    -1.37
     является
    -1.36
     Besonders
    -1.35
    POSITIVE LOGITS
     in
    2.22
     the
    1.88
     to
    1.70
     such
    1.57
     about
    1.56
     including
    1.53
    mpagne
    1.48
    apatalk
    1.48
     studies
    1.48
    olkien
    1.43
    Activations Density 0.013%

    No Known Activations