© 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. 21811
    Prev
    Next
    INDEX
    Explanations

    characters and titles

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

    The neuron fires strongly on capitalized proper names and titles (e.g., people’s names and work titles) in running 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_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
    particularly
    -1.57
     frapp
    -1.54
     alcool
    -1.54
     fondu
    -1.51
     ciment
    -1.48
     rigide
    -1.47
    跸
    -1.45
     diamant
    -1.44
     mostrare
    -1.43
     vinos
    -1.42
    POSITIVE LOGITS
     klassischen
    1.39
     horribly
    1.38
     allmän
    1.30
    Pru
    1.30
    ↵↵
    1.29
     seaside
    1.25
     stereotypical
    1.23
     more
    1.23
     pasirink
    1.23
     unglaub
    1.21
    Activations Density 0.052%

    No Known Activations