© 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. 41-GEMMASCOPE-2-RES-262K
    7. 35417
    Prev
    Next
    INDEX
    Explanations

    variational method

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    tez
    0.35
    tae
    0.35
     प
    0.34
    lasting
    0.33
    uite
    0.33
    ত্যা
    0.33
     ც
    0.33
    ভব
    0.33
    toISOString
    0.33
     meurt
    0.32
    POSITIVE LOGITS
     $=$
    0.45
    >=</
    0.44
    .=
    0.38
     Servicios
    0.37
    =
    0.36
     $=\
    0.35
    [:,
    0.34
     marginally
    0.33
     QUAD
    0.33
     vs
    0.32
    Activations Density 0.002%

    No Known Activations