© 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. 9349
    Prev
    Next
    INDEX
    Explanations

    loss of information

    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
    শ্
    0.39
    udarstven
    0.39
    rocities
    0.38
     absolv
    0.38
    _{+}+
    0.36
    aturday
    0.35
    \;
    0.35
    מן
    0.35
    дел
    0.34
     Metallica
    0.34
    POSITIVE LOGITS
     に
    0.38
     tough
    0.37
     glide
    0.37
     எனப்படும்
    0.37
     exposureButton
    0.37
     marinas
    0.37
     cubes
    0.36
     spices
    0.36
     등이
    0.36
     বনে
    0.36
    Activations Density 0.021%

    No Known Activations