© 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. 239929
    Prev
    Next
    INDEX
    Explanations

    boatloads of, woman in, role of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    服務
    0.46
    資源
    0.46
     Services
    0.46
    喂
    0.46
     SERVICES
    0.44
     \"
    0.44
    धिकारिक
    0.44
    洏
    0.44
     informative
    0.43
    字典
    0.43
    POSITIVE LOGITS
    excess
    0.44
    Excess
    0.44
    Disposition
    0.44
     sensibilidad
    0.44
    ícul
    0.44
    Sensitivity
    0.44
    Suppose
    0.43
    Deal
    0.43
    ArchivePath
    0.43
     வித்தியாச
    0.43
    Activations Density 0.001%

    No Known Activations