© 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. 74628
    Prev
    Next
    INDEX
    Explanations

    technical and analytical phrasing

    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
     polysaccharide
    0.50
     racemic
    0.49
    ܤ
    0.49
     neutralization
    0.47
     polycrystalline
    0.46
     isomerization
    0.46
    餾
    0.45
     intermediaries
    0.45
     ইস্য
    0.45
     অঞ্জু
    0.45
    POSITIVE LOGITS
    Optimize
    0.46
    d
    0.45
    olí
    0.43
    /*
    0.43
    ້ງ
    0.43
    details
    0.42
    UI
    0.41
    :
    0.41
    optimize
    0.41
    el
    0.40
    Activations Density 0.017%

    No Known Activations