© 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. 59458
    Prev
    Next
    INDEX
    Explanations

    should be, truth is

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

    Dota 2

    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
    貸款
    0.40
    saveTool
    0.40
    धित
    0.39
    کروچ
    0.39
     schließlich
    0.38
     couture
    0.38
     دوی
    0.38
    貯
    0.37
    鍔
    0.37
     páginas
    0.37
    POSITIVE LOGITS
    样的
    0.44
     Unless
    0.42
     gcc
    0.42
    дия
    0.40
    ✕
    0.39
    드시
    0.39
     มัน
    0.38
     нельзя
    0.38
     сты
    0.38
    rasz
    0.38
    Activations Density 0.000%

    No Known Activations