© 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. 22-GEMMASCOPE-RES-131K
    7. 67287
    Prev
    Next
    INDEX
    Explanations

    copyright followed by (

    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_22/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
    mistak
    -1.02
     both
    -1.02
     kupić
    -1.02
    假的
    -1.02
     three
    -1.01
     weeks
    -1.01
    センチ
    -0.98
     armées
    -0.96
    duled
    -0.95
     out
    -0.93
    POSITIVE LOGITS
    mmation
    1.08
    нию
    1.05
     anderer
    1.02
     étrange
    1.02
     Некоторые
    1.00
     who
    1.00
    Besos
    1.00
    기도
    1.00
     onItemClick
    0.98
    อื่น
    0.97
    Activations Density 0.437%

    No Known Activations