© 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. 29995
    Prev
    Next
    INDEX
    Explanations

    patent law and immigration

    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
     Senhor
    0.46
     pupp
    0.45
     سعید
    0.43
     zakl
    0.42
    鯛
    0.41
    菜单
    0.41
     swinging
    0.41
    糁
    0.41
     mando
    0.40
     uży
    0.40
    POSITIVE LOGITS
     patent
    0.94
     Patent
    0.89
    Patent
    0.86
    patent
    0.81
    专利
    0.75
     patents
    0.75
     Patents
    0.60
     inventors
    0.56
     patente
    0.56
     filings
    0.55
    Activations Density 0.032%

    No Known Activations