© 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. 22-GEMMASCOPE-RES-131K
    7. 16637
    Prev
    Next
    INDEX
    Explanations

    or, depends, harder

    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
    Negative Logits
     and
    -1.26
    probably
    -1.20
    january
    -1.13
    certainly
    -1.08
    unlike
    -1.05
    ᕮ
    -1.04
    unny
    -1.02
    sibles
    -1.02
    wouldn
    -0.98
    izia
    -0.98
    POSITIVE LOGITS
     or
    1.77
     depending
    1.48
     depends
    1.46
     should
    1.37
     first
    1.33
     if
    1.28
     each
    1.27
     oppure
    1.27
     will
    1.25
     new
    1.15
    Activations Density 0.049%

    No Known Activations