© 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. 47666
    Prev
    Next
    INDEX
    Explanations

    words following conjunctions or punctuation

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

    The neuron strongly activates on numeric and quantitative terminology (e.g. statistical descriptors, measured values, and standalone numbers).

    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
    5
    -2.38
    9
    -2.19
    6
    -1.99
    4
    -1.97
    3
    -1.95
    2
    -1.84
    7
    -1.84
     penderita
    -1.73
    8
    -1.69
     SHAW
    -1.63
    POSITIVE LOGITS
     such
    2.17
     our
    2.05
     those
    2.00
     the
    1.93
     their
    1.75
     any
    1.66
     takim
    1.63
     by
    1.59
     these
    1.53
     of
    1.52
    Activations Density 1.035%

    No Known Activations