© 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. 3231
    Prev
    Next
    INDEX
    Explanations

    I am

    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
    하고자
    0.47
    了解到
    0.46
     naszego
    0.46
     berharap
    0.45
     допомогти
    0.45
     ønsker
    0.43
     느끼
    0.43
     더
    0.43
     njegove
    0.43
     njeg
    0.42
    POSITIVE LOGITS
     is
    0.69
     operates
    0.65
     belongs
    0.64
     contains
    0.62
     consists
    0.61
     was
    0.59
     are
    0.59
     has
    0.55
     isa
    0.55
     exists
    0.54
    Activations Density 0.591%

    No Known Activations