© 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. 10289
    Prev
    Next
    INDEX
    Explanations

    governed by

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

    verbs followed by by

    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
     incul
    0.41
    ទុក
    0.41
    ម្បី
    0.41
     diligently
    0.41
     attributing
    0.39
    ुलर
    0.39
    스럽
    0.39
    丟
    0.38
     কর্তৃপক্ষের
    0.38
    íl
    0.38
    POSITIVE LOGITS
     by
    0.77
     توسط
    0.70
     oleh
    0.65
     bằng
    0.63
     দ্বারা
    0.59
     governed
    0.56
     bych
    0.56
     pelas
    0.55
     द्वारा
    0.54
     svým
    0.54
    Activations Density 0.221%

    No Known Activations