© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65405
    Prev
    Next
    INDEX
    Explanations

    home to / harbors / contains

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

    The neuron consistently lights up on the passage’s key subject noun—typically place names or other domain-specific “headline” nouns that signal the main topic of the paragraph.

    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
    認為
    -0.82
    
    -0.77
     Locale
    -0.75
    entación
    -0.73
    囑
    -0.71
     допомогою
    -0.70
     enters
    -0.70
    认为
    -0.68
    PCell
    -0.68
    šanu
    -0.67
    POSITIVE LOGITS
     hosting
    4.16
     hosts
    3.63
     host
    3.63
     housing
    3.36
    hosting
    3.14
     Hosting
    3.06
     harbor
    3.06
    Hosting
    3.00
     harbour
    2.95
     hosted
    2.88
    Activations Density 0.270%

    No Known Activations