© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40717
    Prev
    Next
    INDEX
    Explanations

    Jewish persecution

    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_65k_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
    id
    0.51
    il
    0.49
    ins
    0.48
    ids
    0.48
    mi
    0.47
    .
    0.45
    domains
    0.42
    س
    0.42
    ها
    0.41
    成绩
    0.41
    POSITIVE LOGITS
     werewolf
    0.53
     κατα
    0.50
     Greeley
    0.50
     Marlene
    0.49
     ке
    0.49
     ポ
    0.49
     October
    0.48
     怪
    0.48
     _____
    0.48
     ウィ
    0.48
    Activations Density 0.002%

    No Known Activations