© 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. 2114
    Prev
    Next
    INDEX
    Explanations

    company, city, guild governance

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ministers
    -0.81
     Ministerial
    -0.79
    哂
    -0.77
     Flexible
    -0.71
     Он
    -0.70
    🫤
    -0.70
     CHAIR
    -0.69
     нашей
    -0.69
    ២
    -0.69
     Ministers
    -0.69
    POSITIVE LOGITS
     guild
    1.53
     guilds
    1.38
    Guild
    1.32
     Guild
    1.31
    guild
    1.20
     Company
    0.98
     city
    0.97
     Incorporation
    0.96
     livery
    0.95
    city
    0.94
    Activations Density 0.053%

    No Known Activations