© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30648
    Prev
    Next
    INDEX
    Explanations

    limitations and difficulties

    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
    Not in Any Lists

    No Comments

    Negative Logits
     dzięki
    -1.16
    不思議
    -1.13
    軽い
    -1.02
     painless
    -0.99
     Благодаря
    -0.98
    不思議な
    -0.97
     différentes
    -0.94
     grâce
    -0.94
    verständlich
    -0.94
    should
    -0.93
    POSITIVE LOGITS
     requires
    1.91
    只能
    1.91
     limited
    1.72
     cannot
    1.71
     only
    1.66
     require
    1.55
     lacks
    1.52
     cumbersome
    1.49
     requiring
    1.38
     unable
    1.36
    Activations Density 0.456%

    No Known Activations