© 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. 16516
    Prev
    Next
    INDEX
    Explanations

    right or left

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

    disclaimer at the end

    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
    矛盾
    0.54
    字符串
    0.52
    ান্তরিত
    0.47
    ية
    0.46
     آخر
    0.46
    ሼ
    0.46
    েকে
    0.45
     الناس
    0.45
    ଙ
    0.45
     কর্মচার
    0.44
    POSITIVE LOGITS
     righth
    0.64
     right
    0.61
     derecho
    0.56
     왼쪽
    0.52
     left
    0.50
     side
    0.50
     право
    0.49
     lefty
    0.49
     правом
    0.48
     sidebar
    0.48
    Activations Density 0.028%

    No Known Activations