© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10873
    Prev
    Next
    INDEX
    Explanations

    Germany German Germany Germany Germany

    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
    Negative Logits
     behem
    1.09
     Medicaid
    1.03
     Yelp
    1.03
     moniker
    1.02
     byproduct
    1.02
     licensure
    1.00
     cognizant
    1.00
     nefarious
    1.00
    ɚ
    1.00
     Craigslist
    1.00
    POSITIVE LOGITS
     German
    1.74
    German
    1.63
     GmbH
    1.57
     (=
    1.47
     Germany
    1.46
     Müller
    1.44
    Germany
    1.42
     Munich
    1.40
     Germans
    1.38
    德国
    1.37
    Activations Density 0.102%

    No Known Activations