© 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-262K
    7. 93300
    Prev
    Next
    INDEX
    Explanations

    TikTok internet slang

    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_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
     Reminder
    0.45
     Defense
    0.41
     Description
    0.41
    आ
    0.41
    อ
    0.41
     Resolution
    0.40
     does
    0.40
     Response
    0.40
     Explanation
    0.40
    Explanation
    0.39
    POSITIVE LOGITS
     ações
    0.50
     receita
    0.48
     anúncios
    0.47
     investimentos
    0.47
     căng
    0.46
     उपभोक्ताओं
    0.46
    𝕥
    0.46
     công
    0.45
     lucru
    0.45
     düğ
    0.45
    Activations Density 0.003%

    No Known Activations