© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69474
    Prev
    Next
    INDEX
    Explanations

    systems, methods, and tools

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

    This neuron detects plural technical nouns referring to methods, tools, devices, or other categorical elements.

    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
    一方
    -1.27
     präsenti
    -1.24
    日閲覧
    -1.21
     сначала
    -1.21
     enviada
    -1.20
    ढ
    -1.19
    ?),
    -1.19
    であり
    -1.17
     caractéris
    -1.16
    éről
    -1.16
    POSITIVE LOGITS
     of
    1.92
     you
    1.84
     for
    1.80
     and
    1.70
     which
    1.48
    Votre
    1.31
     to
    1.30
     that
    1.29
     but
    1.28
     or
    1.23
    Activations Density 0.357%

    No Known Activations