© 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-262K
    7. 127673
    Prev
    Next
    INDEX
    Explanations

    social, cultural, and political entities

    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
    风
    0.46
    얇
    0.46
    丰
    0.45
    itud
    0.44
    山的
    0.44
    乐
    0.44
    roits
    0.43
    发电
    0.43
    飞
    0.42
    战士
    0.41
    POSITIVE LOGITS
     SNS
    0.48
     सगळे
    0.45
     Azerbaijan
    0.44
     sns
    0.44
     antisemit
    0.44
     ASP
    0.43
    izzazione
    0.43
     Flav
    0.42
     Customs
    0.42
     Tunisia
    0.42
    Activations Density 0.009%

    No Known Activations