© 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. 218247
    Prev
    Next
    INDEX
    Explanations

    Nanotechnologies, expense, harmless

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

    rules, states, or connections

    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
     Перейти
    0.51
    ution
    0.48
     ![](
    0.47
    телями
    0.46
     Allí
    0.45
    ᆺ
    0.45
    II
    0.44
    plantation
    0.44
    erland
    0.43
    BGR
    0.42
    POSITIVE LOGITS
    作为一个
    0.53
     potencialmente
    0.50
    作为
    0.48
    भारत
    0.48
    கட
    0.48
     bruto
    0.47
     ensinar
    0.47
     agres
    0.47
     jako
    0.46
    ف
    0.46
    Activations Density 0.001%

    No Known Activations