© 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. 120083
    Prev
    Next
    INDEX
    Explanations

    Mapping Ancient History and Sustainability Theories

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

    a definition

    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
     بنگالی
    0.27
    ො
    0.27
     احمد
    0.26
     Пред
    0.26
     sagen
    0.26
     హిట్
    0.26
     일을
    0.26
     Кри
    0.25
     repositorio
    0.25
     Faculté
    0.25
    POSITIVE LOGITS
    .
    0.34
    ↵↵
    0.28
    ,.
    0.27
     PROVID
    0.26
    加载
    0.26
    ।
    0.26
    ai
    0.26
    不需要
    0.26
    ini
    0.25
    。
    0.25
    Activations Density 0.047%

    No Known Activations