© 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. 111754
    Prev
    Next
    INDEX
    Explanations

    verb conjugations and tenses

    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
     انه
    0.43
    되었
    0.43
    욌
    0.42
    انه
    0.41
     وكانت
    0.40
    jeć
    0.40
     أنها
    0.40
    ᕗ
    0.40
    ances
    0.40
     있었다
    0.39
    POSITIVE LOGITS
     promised
    0.44
     બનાવી
    0.42
    lerdir
    0.40
     boldly
    0.40
     сфор
    0.39
     છે
    0.39
     Headline
    0.39
    Of
    0.38
     Promised
    0.38
    诒
    0.38
    Activations Density 0.002%

    No Known Activations