© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180376
    Prev
    Next
    INDEX
    Explanations

    quality products

    np_acts-logits-general · gemini-2.5-flash-lite

    principles, wisdom, patterns, systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     tried
    0.54
    tried
    0.53
     попробовать
    0.48
    біль
    0.45
     свої
    0.45
    難
    0.45
     надеюсь
    0.44
     konnten
    0.44
    iks
    0.44
    took
    0.43
    POSITIVE LOGITS
    骁
    0.44
     车
    0.43
    것도
    0.42
    情形
    0.41
     infraction
    0.41
     collisions
    0.41
     arithmetic
    0.41
    进程
    0.41
     tabulation
    0.41
    纸
    0.40
    Activations Density 0.001%

    No Known Activations