© 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. 129249
    Prev
    Next
    INDEX
    Explanations

    specific words followed by context

    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
    ちなみに
    0.42
     یا
    0.41
     ።
    0.40
    または
    0.39
    Correction
    0.39
     또는
    0.38
    ጴ
    0.36
     secretly
    0.36
     belongs
    0.36
    리아
    0.36
    POSITIVE LOGITS
     लगाकर
    0.40
    埸
    0.39
    槤
    0.39
     quieras
    0.39
    8
    0.38
    ହା
    0.37
    损害
    0.37
     आग
    0.37
     outset
    0.36
     erc
    0.36
    Activations Density 0.013%

    No Known Activations