© 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. 159002
    Prev
    Next
    INDEX
    Explanations

    sequences like "that you" or "which nurture"

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

    future possibilities and change

    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
    !</
    0.47
     incap
    0.46
    เลข
    0.45
    สรร
    0.45
    !।
    0.45
     Comerc
    0.44
    ..</
    0.44
    嫐
    0.43
     न्यूमेरिकल
    0.42
     alphan
    0.42
    POSITIVE LOGITS
    本科
    0.44
    0.42
    实现了
    0.41
     মুক্তিবাহিনী
    0.41
    其中
    0.40
    Observable
    0.40
    各地
    0.40
    一开始
    0.40
    一路
    0.39
    Legacy
    0.39
    Activations Density 0.000%

    No Known Activations