© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48686
    Prev
    Next
    INDEX
    Explanations

    hands and fingers

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unsecured
    0.53
    మా
    0.50
    集團
    0.48
    互联网档案馆
    0.47
     మొత్త
    0.46
    勰
    0.46
    количество
    0.46
     widths
    0.45
    ጥረ
    0.45
    В
    0.44
    POSITIVE LOGITS
     makanan
    0.54
     muffins
    0.53
    )
    0.51
     kl
    0.47
     goû
    0.46
     vä
    0.45
     Geschmack
    0.45
     latte
    0.45
    )$$
    0.45
    )」
    0.44
    Activations Density 0.002%

    No Known Activations