© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63820
    Prev
    Next
    INDEX
    Explanations

    repeatedly without diminishing

    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_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
      
    0.56
     half
    0.49
     [
    0.47
     of
    0.46
     series
    0.44
     bonds
    0.44
     new
    0.43
     (
    0.43
    izou
    0.43
    (
    0.42
    POSITIVE LOGITS
     ाट
    0.58
    荀
    0.52
    骷
    0.51
     অক্সিজ
    0.49
    autions
    0.48
    出售
    0.48
    防止
    0.47
    𒌅
    0.47
    setNome
    0.46
    㣻
    0.46
    Activations Density 0.004%

    No Known Activations