© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14695
    Prev
    Next
    INDEX
    Explanations

    tried something

    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
     your
    -1.32
     our
    -1.05
     should
    -1.02
     for
    -0.97
    很少
    -0.94
     their
    -0.93
     you
    -0.93
    ätie
    -0.92
     one
    -0.92
     if
    -0.91
    POSITIVE LOGITS
    ทั้ง
    1.46
     både
    1.45
    tried
    1.37
     bahkan
    1.36
     וגם
    1.35
     incluso
    1.33
    甚至
    1.29
     thậm
    1.27
     nawet
    1.24
     but
    1.23
    Activations Density 0.263%

    No Known Activations