© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 297
    Prev
    Next
    INDEX
    Explanations

    punctuations followed by diverse words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }
    0.28
    (
    0.26
    '
    0.26
    /
    0.25
    \
    0.25
                    
    0.24
                     
    0.23
               
    0.23
    Accordingly
    0.23
              
    0.23
    POSITIVE LOGITS
     איך
    0.30
     হ্যাঁ
    0.30
    いろんな
    0.29
     спасибо
    0.29
    maybe
    0.28
     soooo
    0.27
     вони
    0.27
     tudo
    0.27
     bellissimo
    0.27
     wszystko
    0.26
    Activations Density 4.596%

    No Known Activations