© 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-65K
    7. 595
    Prev
    Next
    INDEX
    Explanations

    numbers and slashes

    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_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
     a
    0.25
     _)
    0.24
     ollut
    0.24
    w
    0.23
     n
    0.23
     heeft
    0.23
    า
    0.23
     hanno
    0.23
     NOT
    0.22
    ৭
    0.22
    POSITIVE LOGITS
    шения
    0.22
    taker
    0.22
    chun
    0.21
     инструментов
    0.21
    ív
    0.20
    ként
    0.20
    ten
    0.20
    的大
    0.20
    žas
    0.20
    tin
    0.19
    Activations Density 0.058%

    No Known Activations