© 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. 61812
    Prev
    Next
    INDEX
    Explanations

    adverbs and suffixes like 'ness'

    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
     साथियों
    0.44
     monarch
    0.42
     ऐसी
    0.41
    ╭
    0.40
     coexist
    0.39
    。)
    0.38
     ==
    0.38
    ئ
    0.37
     ostr
    0.37
     생긴
    0.37
    POSITIVE LOGITS
    䀓
    0.43
     galerinha
    0.43
    andelier
    0.42
     parfum
    0.42
     пы
    0.42
    gheatmap
    0.41
     iphdr
    0.41
    Refreshing
    0.41
    の手
    0.40
     текст
    0.40
    Activations Density 0.015%

    No Known Activations