© 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. 22-GEMMASCOPE-RES-131K
    7. 93055
    Prev
    Next
    INDEX
    Explanations

    requesting or explaining reasons

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

    The neuron is primarily detecting common function words—especially high-frequency auxiliaries, prepositions, and articles.

    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
     multicolore
    -0.97
     Grecia
    -0.94
     garan
    -0.94
     palme
    -0.92
     plafon
    -0.92
    vertissement
    -0.87
     salari
    -0.84
     vasi
    -0.84
     torta
    -0.83
     medici
    -0.82
    POSITIVE LOGITS
    请求
    1.08
     demonstrating
    1.06
     request
    0.98
     demostrar
    0.97
     showcasing
    0.94
    requests
    0.93
     pleading
    0.93
     requests
    0.90
     demand
    0.89
     compelling
    0.86
    Activations Density 0.050%

    No Known Activations