© 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. 93842
    Prev
    Next
    INDEX
    Explanations

    news and statistics

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

    The neuron fires strongly on components of Chinese personal names (e.g. “Liu,” “Shao,” “chi,” etc.).

    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
     DataAccess
    -0.86
     seem
    -0.75
    łki
    -0.74
     wouldn
    -0.73
     Schloß
    -0.70
     Configura
    -0.70
     lluvias
    -0.69
    rya
    -0.69
     slight
    -0.69
     weren
    -0.69
    POSITIVE LOGITS
     劉
    0.89
     circumscribed
    0.89
    说
    0.84
     laziness
    0.78
     schizophrenia
    0.78
    莠
    0.77
    Adri
    0.77
    Según
    0.76
    FINAL
    0.76
     sharpen
    0.75
    Activations Density 0.015%

    No Known Activations