© 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. 28531
    Prev
    Next
    INDEX
    Explanations

    comparisons over time

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

    comparison to a baseline

    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
     задач
    0.41
    人們
    0.40
    葦
    0.39
     מכ
    0.39
     ಜೀವ
    0.39
    ရှား
    0.39
    小数
    0.38
    虧
    0.38
    乆
    0.38
     سایر
    0.38
    POSITIVE LOGITS
     baseline
    0.45
     what
    0.45
     ,\
    0.43
    ungen
    0.42
     française
    0.41
    '}}
    0.40
     anno
    0.40
     sunken
    0.40
    ″
    0.39
     entered
    0.38
    Activations Density 0.034%

    No Known Activations