© 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. 31-GEMMASCOPE-2-RES-65K
    7. 55240
    Prev
    Next
    INDEX
    Explanations

    Jewish identity and correlation

    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
    恽
    0.50
    וס
    0.49
    یش
    0.48
     fréqu
    0.48
    ίσ
    0.47
    似的
    0.46
    ті
    0.45
    𝔂
    0.45
    slots
    0.44
    evaluate
    0.44
    POSITIVE LOGITS
     junto
    0.50
    ukkah
    0.50
    than
    0.48
    arden
    0.48
     memper
    0.48
     kudos
    0.46
     penjelasan
    0.45
    
    0.45
     pas
    0.45
     I
    0.44
    Activations Density 0.001%

    No Known Activations