© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49458
    Prev
    Next
    INDEX
    Explanations

    anti-Semitism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    صدار
    -0.80
     still
    -0.80
     दौरान
    -0.77
     sexually
    -0.77
    خره
    -0.73
    Fatalf
    -0.73
    神の
    -0.73
     Babcock
    -0.72
     Taliban
    -0.72
     Bible
    -0.72
    POSITIVE LOGITS
     BDS
    1.38
     Israel
    1.13
     Jew
    1.09
     anti
    1.09
     Jews
    1.06
     יה
    0.96
     анти
    0.96
    Jewish
    0.95
     Jewish
    0.94
     CAMERA
    0.94
    Activations Density 0.031%

    No Known Activations