© 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. 200223
    Prev
    Next
    INDEX
    Explanations

    less frequent, reduce, wrong, life, passenger

    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
    Protein
    0.55
    קו
    0.51
    Gly
    0.50
    4
    0.46
    Motivational
    0.45
    𝗲
    0.45
    е
    0.45
     गावात
    0.45
    <0x0F>
    0.45
    protein
    0.44
    POSITIVE LOGITS
     abraz
    0.60
     pillows
    0.52
     piedras
    0.51
     recrystall
    0.49
     duda
    0.48
     homen
    0.48
     grunds
    0.48
     meubles
    0.48
     piedra
    0.47
     constriction
    0.47
    Activations Density 0.004%

    No Known Activations