© 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. 34-GEMMASCOPE-RES-131K
    7. 90642
    Prev
    Next
    INDEX
    Explanations

    spiritual and ethical concepts

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

    The neuron is selectively activating on very frequent “function” words (common small words like of, is, and, as) rather than content words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    番茄
    -0.82
     Geschmack
    -0.82
    latable
    -0.77
    alten
    -0.77
    cae
    -0.76
    ร์
    -0.75
     sähkö
    -0.72
    setResizable
    -0.71
    zegovina
    -0.70
    אם
    -0.69
    POSITIVE LOGITS
     dharma
    1.62
     Dharma
    1.32
     ahi
    1.11
     Ahi
    1.11
     truth
    1.05
    Truth
    1.01
     Truth
    0.96
     righteousness
    0.95
    righteous
    0.92
     Righteous
    0.92
    Activations Density 0.016%

    No Known Activations