© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127830
    Prev
    Next
    INDEX
    Explanations

    cases including names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    детский
    -1.11
    ibile
    -1.05
    але
    -1.03
    ⽰
    -1.03
    етка
    -1.03
     this
    -1.03
     Polícia
    -1.02
    薷
    -1.02
    atka
    -1.01
     firebaseConfig
    -1.01
    POSITIVE LOGITS
    iyle
    1.16
     květ
    1.13
     rů
    1.02
     Appendix
    1.02
     протягом
    1.00
     initial
    0.98
     [
    0.97
     ребен
    0.92
     formada
    0.91
     смысле
    0.91
    Activations Density 0.010%

    No Known Activations