© 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. 47583
    Prev
    Next
    INDEX
    Explanations

    problematic or harmful content

    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
     দায়িত্ব
    0.46
     মার্
    0.45
     യാത്ര
    0.44
     поезд
    0.43
     жизнь
    0.43
    Ux
    0.43
    Utt
    0.42
    ও
    0.42
    deque
    0.41
    rakech
    0.40
    POSITIVE LOGITS
     offended
    0.60
     violate
    0.57
     luminos
    0.54
     violates
    0.54
     differing
    0.51
     chiar
    0.51
     offend
    0.51
     insensitive
    0.51
     insufficiently
    0.50
     ecce
    0.50
    Activations Density 0.016%

    No Known Activations