© 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. 70500
    Prev
    Next
    INDEX
    Explanations

    introduces common phrases

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

    The neuron strongly activates on lines with very large blocks of leading whitespace (deeply indented lines).

    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
     Preguntas
    -1.17
     escritora
    -1.12
     everyone
    -1.12
     contener
    -1.10
     either
    -1.10
     Opiniones
    -1.08
     warszawa
    -1.07
     expliqué
    -1.06
     безопас
    -1.05
     нажмите
    -1.05
    POSITIVE LOGITS
    wness
    1.08
     רוצה
    1.00
    cyjne
    1.00
     выгля
    0.98
     лимон
    0.96
    辊
    0.94
    𝗗
    0.93
     втор
    0.93
     tekanan
    0.91
    श्यक
    0.90
    Activations Density 0.001%

    No Known Activations