© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10759
    Prev
    Next
    INDEX
    Explanations

    supporters, sympathizers, backing

    np_acts-logits-general · gemini-2.5-flash-lite

    normalization and glorification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بدي
    0.39
    maso
    0.39
    অভি
    0.38
     கொ
    0.37
     complained
    0.37
     জাতিকে
    0.36
    홉
    0.36
    ەم
    0.36
     সোসাই
    0.36
    請求
    0.35
    POSITIVE LOGITS
    支持
    2.23
     ủng
    2.22
     support
    2.05
     apoyo
    2.05
     সমর্থন
    2.05
     समर्थन
    2.00
    support
    1.99
     supportive
    1.96
     supports
    1.95
     支持
    1.94
    Activations Density 0.635%

    No Known Activations