© 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. 402
    Prev
    Next
    INDEX
    Explanations

    the same

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

    The neuron fires on formal patent-style procedural and referential terms—especially words like “method,” “manufacturing,” “same,” “use,” and “therewith.”

    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
     mostrarse
    -0.96
    aragua
    -0.96
     заболевания
    -0.96
     naszym
    -0.95
     poži
    -0.95
     Mitarbeit
    -0.94
     and
    -0.94
    的光
    -0.89
    もしれません
    -0.89
    irls
    -0.87
    POSITIVE LOGITS
     thereof
    1.11
     if
    0.90
    woof
    0.89
     renom
    0.86
     ampli
    0.85
    estä
    0.81
    以及
    0.81
     rodas
    0.78
    stav
    0.78
     Développement
    0.77
    Activations Density 0.071%

    No Known Activations