© 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. 56028
    Prev
    Next
    INDEX
    Explanations

    typedef struct

    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
    I
    0.47
    zh
    0.41
    t
    0.41
    haust
    0.40
    imani
    0.40
     new
    0.39
     insistence
    0.39
    摄
    0.39
    E
    0.38
    IU
    0.38
    POSITIVE LOGITS
    鸪
    0.45
     LOTRAchievement
    0.45
    ۔
    0.44
     주로
    0.44
    จะมี
    0.44
    𒁍
    0.43
    해요
    0.43
    між
    0.43
     おい
    0.43
    会让
    0.43
    Activations Density 0.012%

    No Known Activations