© 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. 60563
    Prev
    Next
    INDEX
    Explanations

    copyright notices and file headers

    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
    他說
    -1.16
     harap
    -1.15
     powiedział
    -1.12
    經常
    -1.10
     voetballer
    -1.10
     sudadera
    -1.09
     sambung
    -1.06
     jonge
    -1.05
     susun
    -1.05
     nyeri
    -1.03
    POSITIVE LOGITS
      
    1.52
     @
    1.38
          
    1.30
         
    1.20
    To
    1.19
    1.18
       
    1.11
              
    1.09
     to
    1.07
           
    1.05
    Activations Density 0.064%

    No Known Activations