© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12009
    Prev
    Next
    INDEX
    Explanations

    reciprocal actions between 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
     pediu
    0.73
     który
    0.64
     multitudes
    0.62
    ي
    0.60
     ejer
    0.59
     indicó
    0.59
    কিন্ত
    0.58
     женой
    0.57
     swojego
    0.56
     پدر
    0.56
    POSITIVE LOGITS
     mutually
    0.53
     in
    0.52
    彼此
    0.50
    相互
    0.49
    Mutual
    0.48
    ä
    0.48
    єї
    0.46
     birbir
    0.45
    einander
    0.45
     through
    0.44
    Activations Density 0.029%

    No Known Activations