© 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. 66727
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
             
    -1.41
    </em>
    -1.39
              
    -1.38
     them
    -1.37
          
    -1.37
           
    -1.36
    m
    -1.35
    ,
    -1.35
         
    -1.33
    se
    -1.30
    POSITIVE LOGITS
     jossa
    1.20
    ymi
    1.16
     primit
    1.16
    Программа
    1.15
    Ostat
    1.12
    contoh
    1.12
    wäh
    1.12
    Това
    1.11
     that
    1.10
    ↓↓
    1.09
    Activations Density 0.148%

    No Known Activations