© 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. 40332
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     extravagant
    -2.36
     observar
    -2.23
     perplexing
    -2.20
     Numerous
    -2.16
     Even
    -2.11
     Generally
    -2.08
     Often
    -2.06
     multifaceted
    -2.03
     endearing
    -2.03
     In
    -2.03
    POSITIVE LOGITS
    e
    2.75
    of
    2.27
    女孩子
    2.19
    
    2.17
    to
    2.14
    ’
    2.13
     faſt
    2.08
     passando
    2.08
    蠖
    2.06
    i
    2.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.