© 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. 53-GEMMASCOPE-2-RES-262K
    7. 35405
    Prev
    Next
    INDEX
    Explanations

    Greek particles and prefixes

    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_53_width_262k_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
     został
    0.40
    葵
    0.39
    osph
    0.38
     turtle
    0.38
    セント
    0.37
     stick
    0.37
     Yok
    0.37
     Turtle
    0.37
     quadru
    0.37
     turt
    0.36
    POSITIVE LOGITS
     έκ
    0.52
    ποίη
    0.51
     діа
    0.49
     диа
    0.45
     πρόσ
    0.43
    ὕ
    0.42
    Cas
    0.39
     metastasis
    0.39
     επέ
    0.39
    állítás
    0.38
    Activations Density 0.001%

    No Known Activations