© 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. 12193
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives suffixed with y

    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
     a
    0.81
     I
    0.77
     A
    0.75
     T
    0.71
     R
    0.65
    a
    0.64
     P
    0.63
     O
    0.63
     S
    0.61
     B
    0.61
    POSITIVE LOGITS
    도
    0.91
    在
    0.88
    ও
    0.87
     in
    0.75
    も
    0.74
     σε
    0.61
    。
    0.60
    的
    0.56
     في
    0.55
    માં
    0.55
    Activations Density 0.077%

    No Known Activations