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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17120
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and Than

    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
    ，
    0.81
    。
    0.79
    と
    0.77
    ।
    0.67
    ،
    0.66
    과
    0.66
    ？
    0.63
    0.62
    ：
    0.62
    、
    0.61
    POSITIVE LOGITS
     deeper
    0.74
     Than
    0.72
    ла
    0.69
    Than
    0.67
    િ
    0.66
     quieter
    0.66
     than
    0.66
    助于
    0.64
    ли
    0.63
    ো
    0.63
    Activations Density 0.222%

    No Known Activations