© 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. 176989
    Prev
    Next
    INDEX
    Explanations

    legal declarations or specific events

    np_acts-logits-general · gemini-2.5-flash-lite

    golden cage/shadow concepts

    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
    körper
    0.50
    stv
    0.50
    ер
    0.49
     urbano
    0.49
    cartes
    0.48
    unuz
    0.48
    ਸ਼
    0.47
    z
    0.47
    व्ह
    0.46
    negara
    0.46
    POSITIVE LOGITS
     Genomic
    0.46
     Appendix
    0.45
     Thermodynamic
    0.44
     Instead
    0.44
     Hour
    0.44
     Strategic
    0.44
     Publishing
    0.43
     Append
    0.43
     Reservoir
    0.43
     Research
    0.42
    Activations Density 0.001%

    No Known Activations