© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250552
    Prev
    Next
    INDEX
    Explanations

    mentors, contributors, racial prejudice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    bestroute
    0.59
    間違い
    0.51
    て
    0.51
    確保
    0.51
    たくさんの
    0.50
    brix
    0.50
    させ
    0.49
    テ
    0.49
    が多い
    0.48
    benar
    0.48
    POSITIVE LOGITS
     Trainer
    0.52
     Context
    0.51
     Method
    0.50
     exponent
    0.49
     List
    0.48
     Objective
    0.48
    List
    0.47
    Context
    0.45
     Physical
    0.44
    仅
    0.44
    Activations Density 0.001%

    No Known Activations