© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134953
    Prev
    Next
    INDEX
    Explanations

    Judaism, Jewish people, Hebrew

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    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
     Vatican
    0.42
     Catholic
    0.40
    Catholic
    0.39
    Gain
    0.38
     প্যার
    0.38
    Saturation
    0.38
    睃
    0.38
    酆
    0.38
    మారు
    0.38
     Landry
    0.37
    POSITIVE LOGITS
     Jewish
    1.48
    Jewish
    1.36
     Judaism
    1.19
     Jews
    1.16
     اليه
    1.16
     Hebrew
    1.13
     евре
    1.13
     judíos
    1.10
    以色列
    1.06
     Israeli
    1.05
    Activations Density 0.000%

    No Known Activations