© 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. 86821
    Prev
    Next
    INDEX
    Explanations

    names, surnames, and compound words

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

    The neuron selectively fires on uncommon proper names (especially character or place names) in the text.

    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
     both
    -1.07
     make
    -1.07
     where
    -1.03
     that
    -0.99
     this
    -0.98
     improve
    -0.96
     get
    -0.93
     does
    -0.93
     utilize
    -0.92
     demonstrate
    -0.91
    POSITIVE LOGITS
    gül
    1.05
    𓁹
    1.02
     koment
    1.02
    freund
    0.98
    baden
    0.97
    artement
    0.96
    werben
    0.95
     konkuren
    0.94
    rovna
    0.94
     میلیارد
    0.93
    Activations Density 0.047%

    No Known Activations