© 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. 22-GEMMASCOPE-RES-131K
    4. 28067
    Prev
    Next
    INDEX
    Explanations

    URLs, citations, institutional affiliations

    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
     comprehen
    -1.05
    N
    -1.02
     Improves
    -1.02
    ༈
    -1.00
     به‌
    -0.98
     astonishing
    -0.96
     gewel
    -0.96
    还能
    -0.95
    </h1>
    -0.94
    Ii
    -0.94
    POSITIVE LOGITS
     Both
    1.27
     by
    1.21
     when
    1.04
     gets
    1.00
    !!!!!
    0.97
     there
    0.96
     as
    0.94
    Both
    0.94
     burgeoning
    0.94
     Ironically
    0.91
    Activations Density 0.076%

    No Known Activations