© 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. 34-GEMMASCOPE-RES-131K
    4. 66149
    Prev
    Next
    INDEX
    Explanations

    birth, renewal, and transformation

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

    concepts related to transformation, change, renewal, and cycles of life and death.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on words that evoke change, renewal, or cyclical transitions—terms like “year,” “cycles,” “birth,” “death,” “new,” “renewal,” “change,” and “transformation.”

    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
     счастья
    -0.93
    iritto
    -0.86
     kant
    -0.84
     market
    -0.84
    kový
    -0.82
    happiness
    -0.80
    に住
    -0.80
    参赛
    -0.79
     сча
    -0.79
    meditation
    -0.79
    POSITIVE LOGITS
     rebirth
    2.80
     birth
    2.44
     reborn
    2.19
    birth
    1.94
     phoenix
    1.91
     renewal
    1.80
     Rebirth
    1.77
     births
    1.70
    BIRTH
    1.65
     regeneration
    1.62
    Activations Density 0.035%

    No Known Activations