© 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-65K
    7. 52810
    Prev
    Next
    INDEX
    Explanations

    LaTeX align and equation environments

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     "/")
    0.55
     மட்டும்
    0.50
     navegador
    0.49
     ".")
    0.46
     {})
    0.46
     മത
    0.45
     integrante
    0.44
     söyl
    0.43
     enseñar
    0.42
    gesterone
    0.42
    POSITIVE LOGITS
     Много
    0.47
    و
    0.45
    os
    0.45
    multi
    0.44
    जल
    0.42
    Multiline
    0.41
    aligned
    0.41
    align
    0.39
    mult
    0.39
     多
    0.39
    Activations Density 0.001%

    No Known Activations