© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13926
    Prev
    Next
    INDEX
    Explanations

    people involved in a situation

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

    entities involved in a process

    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_31_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
    нет
    0.52
    ității
    0.50
    <unused21>
    0.48
    öffentlichung
    0.48
    生まれ
    0.47
    넷
    0.47
    装
    0.46
    trajectory
    0.46
    ネット
    0.46
    𝗯
    0.46
    POSITIVE LOGITS
     soggetti
    0.48
     commandes
    0.48
     grafik
    0.48
     didik
    0.47
     contenders
    0.46
     berupa
    0.45
     kb
    0.44
     metter
    0.44
    বস্ত
    0.44
     trees
    0.44
    Activations Density 0.746%

    No Known Activations