© 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. 94905
    Prev
    Next
    INDEX
    Explanations

    agents, uncertainty, contingent

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

    chooses to learn with team

    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
    码
    0.55
     “…
    0.50
    एशन
    0.50
    وں
    0.48
     эн
    0.48
    ंकर
    0.47
    ونم
    0.47
     köny
    0.47
     หนึ่ง
    0.46
     exe
    0.46
    POSITIVE LOGITS
    。）
    0.49
    まさ
    0.47
    評價
    0.46
     conclusive
    0.45
    機會
    0.45
    Ė
    0.45
    RIO
    0.44
    ে
    0.44
     режиме
    0.43
     Kegiatan
    0.43
    Activations Density 0.000%

    No Known Activations