© 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. 127892
    Prev
    Next
    INDEX
    Explanations

    create and build

    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
    despite
    -1.92
    slightly
    -1.64
     especializada
    -1.58
     egens
    -1.54
     jego
    -1.54
    それは
    -1.54
    但是在
    -1.46
    姈
    -1.45
    albeit
    -1.45
    frequently
    -1.44
    POSITIVE LOGITS
     a
    4.28
     an
    3.08
    #%%
    1.88
     and
    1.55
     også
    1.55
     better
    1.48
    </i>
    1.45
    úmenes
    1.41
    </em>
    1.39
     more
    1.37
    Activations Density 0.058%

    No Known Activations