© 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. 65580
    Prev
    Next
    INDEX
    Explanations

    specific classifications after 'of'

    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
    住宅
    -0.83
     シャ
    -0.75
     — 
    -0.73
     Loot
    -0.73
    chak
    -0.70
     coucher
    -0.70
    volvement
    -0.69
    筊
    -0.68
     kredit
    -0.68
     Shores
    -0.68
    POSITIVE LOGITS
     first
    1.09
     higher
    1.08
     общего
    1.06
     первой
    1.05
     second
    1.05
     pierwszej
    1.03
     wysok
    1.01
     повышен
    1.00
     high
    0.98
     první
    0.97
    Activations Density 0.081%

    No Known Activations