© 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. 101782
    Prev
    Next
    INDEX
    Explanations

    determiners followed by nouns

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

    This neuron detects numeric measurements and quantities (especially decimal values and counts) in technical or descriptive contexts.

    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
     to
    -1.91
    manın
    -1.48
    了一個
    -1.37
    pullover
    -1.37
     for
    -1.34
    Джере
    -1.33
     see
    -1.31
    gilet
    -1.31
     than
    -1.27
    íodo
    -1.27
    POSITIVE LOGITS
     my
    1.84
    voyez
    1.47
     vuestra
    1.42
     मैंने
    1.40
    nému
    1.38
    nament
    1.34
    quelles
    1.23
     we
    1.23
     vuestro
    1.21
     trozos
    1.21
    Activations Density 0.262%

    No Known Activations