© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31592
    Prev
    Next
    INDEX
    Explanations

    verbs ending in ed followed by by

    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_40_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
    由
    0.47
     توسط
    0.43
    からの
    0.42
     由
    0.42
    是由
    0.40
     بواسطة
    0.40
    ENG
    0.39
     pelos
    0.39
     কর্তৃক
    0.38
    ंकडून
    0.38
    POSITIVE LOGITS
    clusively
    0.42
     entirely
    0.41
    рий
    0.41
    chließlich
    0.41
     unapolog
    0.41
     entirety
    0.40
    ᆹ
    0.39
    ('\\
    0.39
    itatively
    0.38
    inkan
    0.38
    Activations Density 0.005%

    No Known Activations