© 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. 85593
    Prev
    Next
    INDEX
    Explanations

    state law

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

    building blocks of life

    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
    柟
    0.48
     comparability
    0.42
     gardener
    0.42
     zw
    0.41
    σιμοποι
    0.41
     hầu
    0.41
     guard
    0.41
     toilet
    0.40
    fü
    0.40
    家居
    0.40
    POSITIVE LOGITS
     lanjutkan
    0.51
     زیرا
    0.48
    வரி
    0.47
    REDIRECT
    0.47
    MM
    0.46
    ➣
    0.46
    ﻴ
    0.46
    🔽
    0.46
    ک
    0.45
    arsa
    0.45
    Activations Density 0.001%

    No Known Activations