© 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. 70063
    Prev
    Next
    INDEX
    Explanations

    our business

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

    It was that confidence

    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
    ي
    0.58
    i
    0.54
    Una
    0.49
    އ
    0.49
    Bundes
    0.47
    Ai
    0.47
     mold
    0.46
    Mold
    0.45
     will
    0.44
    ع
    0.44
    POSITIVE LOGITS
    tBleStatus
    0.50
     বাঙালি
    0.49
    畀
    0.47
    ède
    0.47
     дописавши
    0.47
     FEATURE
    0.46
     CONNECTION
    0.44
    ੯
    0.44
    並沒有
    0.44
    波動方程式
    0.43
    Activations Density 0.000%

    No Known Activations