© 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. 127696
    Prev
    Next
    INDEX
    Explanations

    optionality or nullability

    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
     from
    -1.05
     别墅
    -0.96
     passwd
    -0.96
    icides
    -0.92
    idenav
    -0.91
    sharing
    -0.90
    terrasse
    -0.89
     nasıl
    -0.88
    melons
    -0.86
    Ḱ
    -0.84
    POSITIVE LOGITS
     optional
    1.18
     flexible
    0.97
    ẵ
    0.89
     позволя
    0.88
     vás
    0.88
     gracefully
    0.88
     Entre
    0.87
     وجود
    0.85
     facult
    0.84
     pousse
    0.84
    Activations Density 0.033%

    No Known Activations