© 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. 127951
    Prev
    Next
    INDEX
    Explanations

    or, because, but, rather than

    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
    Not in Any Lists

    No Comments

    Negative Logits
     चाह
    -0.99
     Charlottesville
    -0.98
    わけではない
    -0.91
    楽しむ
    -0.87
     құ
    -0.87
     қа
    -0.84
    ोट
    -0.83
    ők
    -0.82
     umgangssprach
    -0.81
    M
    -0.81
    POSITIVE LOGITS
     or
    1.30
    หรือ
    1.24
     или
    1.20
     یا
    1.20
     merely
    1.06
     потому
    1.03
     rijk
    1.03
     karena
    1.03
    нгредіє
    1.03
     porque
    1.02
    Activations Density 0.054%

    No Known Activations