© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128734
    Prev
    Next
    INDEX
    Explanations

    comparing quantities or amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主な
    -1.04
    savevideo
    -0.98
     many
    -0.92
     this
    -0.91
    Що
    -0.91
     sok
    -0.88
     juga
    -0.87
    🧾
    -0.87
     clientes
    -0.86
    đại
    -0.86
    POSITIVE LOGITS
     compared
    1.34
    の方が
    1.13
    比
    1.09
     decât
    1.08
     better
    1.05
     نسبت
    1.02
     than
    1.01
    Compared
    0.99
    jercicios
    0.99
     Joaqu
    0.98
    Activations Density 0.075%

    No Known Activations