© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9884
    Prev
    Next
    INDEX
    Explanations

    absolute value or magnitude

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

    absolute difference and magnitude

    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_40_width_16k_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
    ায়ণ
    0.40
     প্রস
    0.39
    ঙালি
    0.38
    ాత్ర
    0.37
    ষ্টার
    0.37
    earance
    0.37
    굼
    0.37
    জমেন্ট
    0.36
    thomas
    0.36
    लक्ष्मी
    0.36
    POSITIVE LOGITS
     absolute
    2.02
    absolute
    1.93
     Absolute
    1.89
     абсолю
    1.85
    Absolute
    1.84
    绝对
    1.81
     absol
    1.74
    絶対
    1.70
     absolue
    1.68
     $|
    1.67
    Activations Density 0.082%

    No Known Activations