© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 48496
    Prev
    Next
    INDEX
    Explanations

    founded by; seeing ads; relationship between

    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
    extractor
    0.50
    ಮ್
    0.48
     sparring
    0.46
     decenas
    0.46
     grandma
    0.45
     fluido
    0.45
     granny
    0.45
    𝗲
    0.45
     всіх
    0.45
     altres
    0.45
    POSITIVE LOGITS
     melakukannya
    0.41
     غالب
    0.41
     ситуа
    0.40
    认可
    0.39
    ysseus
    0.39
    延续
    0.39
     aktu
    0.37
     احتم
    0.37
     தமது
    0.37
    ヶ
    0.37
    Activations Density 0.002%

    No Known Activations