© 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-16K
    4. 102
    Prev
    Next
    INDEX
    Explanations

    multilingual technical terms

    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
     {
    0.25
    estinal
    0.22
    oddsidemargin
    0.22
    y
    0.21
      
    0.21
     irradiated
    0.21
    dx
    0.20
    a
    0.20
     असलेला
    0.20
    _(
    0.20
    POSITIVE LOGITS
     bicovariant
    0.27
     नौ
    0.25
     അ
    0.25
     vacanam
    0.25
     utilisant
    0.24
    春
    0.23
     Unlike
    0.23
    Using
    0.23
    Ach
    0.23
     dezvolt
    0.23
    Activations Density 5.245%

    No Known Activations