© 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. 16-GEMMASCOPE-2-RES-262K
    7. 32040
    Prev
    Next
    INDEX
    Explanations

    code syntax delimiters

    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_16_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
    )
    0.59
     利用
    0.59
    зме
    0.58
    кс
    0.52
    вими
    0.51
     sited
    0.51
    ]
    0.50
    规范
    0.48
    δι
    0.48
     Список
    0.48
    POSITIVE LOGITS
     цена
    0.62
    ที่
    0.59
    iert
    0.55
    ع
    0.55
    enie
    0.54
    에
    0.54
    ně
    0.53
    เพราะ
    0.52
    alena
    0.52
    がいる
    0.51
    Activations Density 0.047%

    No Known Activations