© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22685
    Prev
    Next
    INDEX
    Explanations

    speech and 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     these
    -1.73
     when
    -1.61
     attenzione
    -1.55
     then
    -1.44
     These
    -1.36
     like
    -1.35
    是非常
    -1.32
    lijden
    -1.30
     prestazioni
    -1.29
    των
    -1.27
    POSITIVE LOGITS
    了一眼
    1.34
     which
    1.30
     and
    1.30
    .
    1.30
     I
    1.26
     or
    1.25
            
    1.20
       
    1.20
    楽しめます
    1.19
    Greater
    1.13
    Activations Density 0.097%

    No Known Activations