© 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. 237531
    Prev
    Next
    INDEX
    Explanations

    multilingual applications and percentages

    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
    ꞎ
    0.55
    മാണ
    0.46
    長期
    0.46
    taxonomy
    0.46
    design
    0.45
     становништво
    0.45
    の影響
    0.45
    觜
    0.45
     unatt
    0.45
    leap
    0.45
    POSITIVE LOGITS
    rai
    0.49
     Cached
    0.47
    ak
    0.45
    larak
    0.44
     önem
    0.44
    ariş
    0.44
     ነገር
    0.43
     প্রচারিত
    0.43
    ikken
    0.42
     কাছে
    0.42
    Activations Density 0.001%

    No Known Activations