© 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. 5488
    Prev
    Next
    INDEX
    Explanations

    roughly, approximately, about

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

    approximations and ranges

    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
     পাইয়া
    0.44
    妵
    0.43
     করিলে
    0.40
     nitric
    0.40
     Nhật
    0.40
    <unused95>
    0.39
     enseign
    0.39
    <unused1>
    0.38
     appliquée
    0.38
     została
    0.38
    POSITIVE LOGITS
     примерно
    0.89
     roughly
    0.87
    ประมาณ
    0.82
     ประมาณ
    0.82
    大概
    0.80
    差不多
    0.80
    大约
    0.79
     ongeveer
    0.79
    roughly
    0.76
    或
    0.76
    Activations Density 0.203%

    No Known Activations