© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 98639
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotes

    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
    licopter
    -2.22
     siè
    -2.19
     charmant
    -2.17
     célè
    -2.17
     pittores
    -2.13
    provides
    -2.11
    
    -2.08
    usually
    -2.06
     épar
    -2.05
     régal
    -2.05
    POSITIVE LOGITS
     on
    2.91
     and
    2.88
     will
    2.77
     at
    2.75
     using
    2.63
     this
    2.61
     with
    2.59
     it
    2.55
     use
    2.52
     out
    2.48
    Activations Density 0.041%

    No Known Activations