© 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. 10-GEMMASCOPE-RES-131K
    7. 74943
    Prev
    Next
    INDEX
    Explanations

    i followed by c g

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

    The neuron activates on the single‐character lowercase token “i.”

    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
    an
    -3.55
    D
    -3.13
    n
    -3.08
    鋮
    -2.98
     exuberant
    -2.95
    ↵↵
    -2.94
     exquisitely
    -2.91
     formidable
    -2.75
     multifaceted
    -2.72
    ve
    -2.67
    POSITIVE LOGITS
     ใน
    2.91
    缡
    2.80
     avem
    2.58
    艄
    2.58
    つた
    2.53
    の人は
    2.52
    肏
    2.48
    歘
    2.45
     promove
    2.45
     comunica
    2.45
    Activations Density 0.001%

    No Known Activations