© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201951
    Prev
    Next
    INDEX
    Explanations

    ethnicity and race

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     flexDirection
    0.41
     prvo
    0.40
     concentration
    0.36
     geopol
    0.35
     Associated
    0.35
    ทรง
    0.34
     বদ্ধ
    0.34
    鶚
    0.34
    xml
    0.33
     paris
    0.33
    POSITIVE LOGITS
     Koreans
    0.51
     natomiast
    0.47
    ๅ
    0.47
    wikk
    0.46
    善良
    0.45
     llegará
    0.45
    ják
    0.44
    నుంది
    0.44
    cuits
    0.44
     malah
    0.44
    Activations Density 0.007%

    No Known Activations