© 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. 123810
    Prev
    Next
    INDEX
    Explanations

    diseased humans

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

    bundling together, backup

    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
     طريقة
    0.49
     점
    0.46
     Що
    0.46
     Leur
    0.46
    ượu
    0.45
    觧
    0.45
     Букмекер
    0.44
    珴
    0.44
     способы
    0.43
     осигурање
    0.43
    POSITIVE LOGITS
     partner
    0.50
     years
    0.46
     countries
    0.45
    partner
    0.45
    CPU
    0.45
     Partner
    0.43
     diaspora
    0.43
     llamados
    0.43
     microcontroller
    0.43
     factories
    0.42
    Activations Density 0.001%

    No Known Activations