© 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-16K
    7. 11723
    Prev
    Next
    INDEX
    Explanations

    for loops and comprehensions

    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_16k_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
    ే
    0.57
     infotainment
    0.48
     simak
    0.48
     remember
    0.45
    o
    0.45
    đer
    0.45
     movimiento
    0.45
     projeto
    0.45
     coni
    0.44
    َ
    0.44
    POSITIVE LOGITS
    CBUUID
    0.44
    पुर
    0.42
    置
    0.42
     पाएगा
    0.41
    産業
    0.40
    ")]
    0.39
    ᾳ
    0.39
    将
    0.39
    "))
    0.38
     diver
    0.38
    Activations Density 0.034%

    No Known Activations