© 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. 22-GEMMASCOPE-RES-131K
    4. 93047
    Prev
    Next
    INDEX
    Explanations

    names, dates, web technologies

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

    The neuron activates on tokens naming core .NET framework namespaces (e.g. “Net”, “Data”, “Web”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     or
    -2.02
     During
    -1.57
     and
    -1.55
     any
    -1.52
     all
    -1.44
     before
    -1.43
     its
    -1.41
    づけ
    -1.39
     Before
    -1.38
     every
    -1.37
    POSITIVE LOGITS
    1.80
    镲
    1.52
    骉
    1.47
     &
    1.45
     längere
    1.45
    --
    1.45
    з
    1.44
    ly
    1.41
     angewendet
    1.39
    х
    1.38
    Activations Density 0.000%

    No Known Activations