© 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. 30490
    Prev
    Next
    INDEX
    Explanations

    He, she, or I

    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
     финансовых
    0.43
     пришли
    0.40
    摑
    0.40
     Loyola
    0.40
     제조업
    0.40
     సంస్థ
    0.39
    ศรี
    0.39
     MongoClient
    0.38
    묭
    0.38
     মাছ
    0.38
    POSITIVE LOGITS
    age
    0.42
    uki
    0.41
    兼
    0.40
     occasional
    0.40
     annual
    0.39
    annual
    0.39
    order
    0.39
     सालाना
    0.39
     secretly
    0.39
    ervi
    0.39
    Activations Density 0.100%

    No Known Activations