© 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. 4344
    Prev
    Next
    INDEX
    Explanations

    short or small items

    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
     Į
    0.49
    สู่
    0.47
    の両
    0.47
    та
    0.46
    łaszcza
    0.46
     pengguna
    0.46
     LONG
    0.46
     tujuh
    0.46
     became
    0.45
    ാവ
    0.45
    POSITIVE LOGITS
    pox
    0.62
     gọn
    0.59
     simple
    0.57
     (<
    0.57
    简单的
    0.57
    簡單
    0.56
    小的
    0.55
     $(<
    0.55
    (<
    0.54
     nhàng
    0.53
    Activations Density 0.312%

    No Known Activations