© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3393
    Prev
    Next
    INDEX
    Explanations

    about creative works

    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
    ش
    0.38
    et
    0.38
     تمامی
    0.37
    ğı
    0.37
    äure
    0.37
     fondant
    0.36
    ation
    0.36
    ate
    0.36
     ठिकाणी
    0.35
     फिल्मी
    0.35
    POSITIVE LOGITS
     about
    0.51
     tentang
    0.50
    📄
    0.49
     konusu
    0.47
     acerca
    0.46
     về
    0.45
     عن
    0.45
     apie
    0.45
     written
    0.43
    或
    0.43
    Activations Density 0.266%

    No Known Activations