© 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. 21800
    Prev
    Next
    INDEX
    Explanations

    random color generation

    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
     כל
    0.38
     л
    0.37
    effer
    0.37
    🤌
    0.37
     알
    0.36
    蒡
    0.35
    🗝
    0.35
     бле
    0.35
    ENCI
    0.35
    집
    0.35
    POSITIVE LOGITS
     similarly
    0.72
    同样
    0.66
    同樣
    0.65
     again
    0.61
     Similarly
    0.57
     likewise
    0.57
     Again
    0.57
     ebenfalls
    0.55
    こちらも
    0.55
     similar
    0.54
    Activations Density 0.082%

    No Known Activations