© 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. 17-GEMMASCOPE-2-RES-16K
    7. 15927
    Prev
    Next
    INDEX
    Explanations

    corporate legal structures

    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_17_width_16k_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
     ischemia
    1.13
     gradients
    1.08
     aérea
    1.08
     cardiaque
    1.07
     aspectRatio
    1.05
     photons
    1.05
     télévision
    1.04
    纜
    1.03
     invalidated
    1.02
     televisão
    1.02
    POSITIVE LOGITS
     Business
    1.17
     LLC
    1.17
     business
    1.14
    Business
    1.06
     юриди
    1.04
    Legal
    1.02
     legal
    1.01
     Legal
    1.00
    business
    0.99
    設立
    0.97
    Activations Density 0.143%

    No Known Activations