© 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. 10-GEMMASCOPE-RES-131K
    4. 75374
    Prev
    Next
    INDEX
    Explanations

    new era, beginning, life

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

    The neuron fires on phrases that announce or label the start of a “new era” or “new beginning.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -1.56
     detención
    -1.55
      
    -1.40
    so
    -1.32
     сейчас
    -1.31
    m
    -1.31
     such
    -1.30
    while
    -1.30
     mientras
    -1.29
     to
    -1.27
    POSITIVE LOGITS
    रीदारी
    1.41
    Ꮟ
    1.40
    劉
    1.39
    新的
    1.38
     BitmapFactory
    1.36
    راین
    1.33
    ſelves
    1.33
     possibilidades
    1.32
     tuta
    1.30
     partnership
    1.30
    Activations Density 0.026%

    No Known Activations