© 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. 34-GEMMASCOPE-RES-131K
    7. 106205
    Prev
    Next
    INDEX
    Explanations

    zip

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    olish
    -0.89
     saída
    -0.84
     candid
    -0.80
     гостей
    -0.80
    Compound
    -0.78
    Gbps
    -0.77
    tesi
    -0.77
    bpf
    -0.77
     colossal
    -0.76
     ا
    -0.76
    POSITIVE LOGITS
     Zip
    1.34
     unzip
    1.18
     zip
    1.11
     zipped
    1.08
     ZIP
    1.08
    Zip
    0.85
    ZIP
    0.85
    zip
    0.84
    metology
    0.82
    unzi
    0.81
    Activations Density 0.009%

    No Known Activations