© 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. 71960
    Prev
    Next
    INDEX
    Explanations

    will focus on

    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
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -1.66
     if
    -1.39
    -
    -1.38
    ?
    -1.30
     maybe
    -1.27
       
    -1.23
     one
    -1.21
     might
    -1.20
     six
    -1.20
     I
    -1.17
    POSITIVE LOGITS
     réfrig
    1.44
    
    1.38
     étan
    1.38
    mueble
    1.30
     huiles
    1.28
    Anda
    1.26
    داشت
    1.25
     éché
    1.24
    Externé
    1.24
    voyez
    1.24
    Activations Density 0.089%

    No Known Activations