© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3699
    Prev
    Next
    INDEX
    Explanations

    laws and regulations

    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_29_width_65k_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
    ْ
    0.60
    ﻮ
    0.56
    Theoretical
    0.56
    Vector
    0.56
    Recipes
    0.55
     lexical
    0.55
    애
    0.55
    㹮
    0.55
    Region
    0.55
    Infer
    0.55
    POSITIVE LOGITS
     exemptions
    1.07
     agreements
    1.06
     exemption
    1.01
     laws
    1.00
     regulations
    0.99
     provisions
    0.97
     waivers
    0.96
     reforms
    0.94
     notices
    0.93
     protections
    0.93
    Activations Density 0.184%

    No Known Activations