© 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. 72533
    Prev
    Next
    INDEX
    Explanations

    chance, artist, formation, third, information

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

    import numpy

    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
    壹百
    0.52
    上面的
    0.49
     Số
    0.45
    ર્સ
    0.44
     técnicos
    0.44
     হাইড্রোজেন
    0.44
    趙
    0.44
     સૌથી
    0.43
    幹
    0.43
    致命
    0.42
    POSITIVE LOGITS
     ஏற்ப
    0.39
     पुनः
    0.39
    discharge
    0.39
     yeniden
    0.39
     ভ্রমণ
    0.38
     সম্প্রদ
    0.38
    periods
    0.38
     cooperative
    0.38
     transients
    0.38
    Ku
    0.38
    Activations Density 0.001%

    No Known Activations