© 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. 21047
    Prev
    Next
    INDEX
    Explanations

    making clearer or easier

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

    easier, more readable, clearer

    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
     കല
    0.38
     ಮನೆಯ
    0.38
     വിള
    0.38
     ежедневно
    0.36
    の手
    0.36
    érapie
    0.36
    日から
    0.35
    宮
    0.35
    ándole
    0.34
    ೋಗ
    0.34
    POSITIVE LOGITS
     easier
    0.67
    更容易
    0.60
     unambiguously
    0.49
     more
    0.49
     Easier
    0.47
     легче
    0.47
     nicer
    0.45
     более
    0.45
     richer
    0.45
     cleanly
    0.45
    Activations Density 0.001%

    No Known Activations