© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13640
    Prev
    Next
    INDEX
    Explanations

    setting up how to proceed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exacerbate
    0.86
     प्रभावी
    0.79
    Robust
    0.78
    derived
    0.78
     эффективно
    0.78
     efficacement
    0.77
    
    0.77
    近年
    0.77
    Strong
    0.76
    enberg
    0.76
    POSITIVE LOGITS
     instructions
    1.12
     formalities
    1.04
     first
    1.04
     prelude
    0.96
     Instructions
    0.95
     prelimin
    0.95
     directions
    0.90
     என்னுடைய
    0.89
     prerequisites
    0.89
     terlebih
    0.88
    Activations Density 0.282%

    No Known Activations