© 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. 6566
    Prev
    Next
    INDEX
    Explanations

    legal and financial proceedings

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

    actions requiring immediate action

    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
     ዋና
    0.56
     ሁሉም
    0.56
    愀
    0.54
    า
    0.53
    ั่ง
    0.52
    לו
    0.52
    ﹉
    0.51
    ajemy
    0.51
     ہم
    0.50
    ྥ
    0.50
    POSITIVE LOGITS
     Brexit
    0.58
     Medicaid
    0.53
     fraud
    0.50
     disagreed
    0.50
    constitutional
    0.50
     claims
    0.50
     equities
    0.49
     criminal
    0.49
     hardship
    0.49
     reconsider
    0.49
    Activations Density 0.134%

    No Known Activations