© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87751
    Prev
    Next
    INDEX
    Explanations

    deck containing, Recovery Mode, Florida kept, front pocket, design feature

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

    after words in other languages

    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_262k_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
     করিয়াছি
    0.55
    檀
    0.48
     january
    0.47
    啦
    0.46
    因素
    0.45
    жим
    0.45
     фактор
    0.44
    证据
    0.43
    幅
    0.43
    ству
    0.42
    POSITIVE LOGITS
     Após
    0.54
     erricht
    0.54
     setelah
    0.51
     Setelah
    0.49
     Dopo
    0.48
     después
    0.47
     Während
    0.47
     çö
    0.47
     berdiri
    0.47
     Después
    0.46
    Activations Density 0.001%

    No Known Activations