© 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. 144335
    Prev
    Next
    INDEX
    Explanations

    purchase options

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

    pressures or possibility

    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
     экономического
    0.50
     экономических
    0.48
    экономи
    0.48
    त
    0.46
     ৪৫
    0.46
     HomeController
    0.46
    addTask
    0.45
    т
    0.45
    ிறது
    0.44
    τικών
    0.44
    POSITIVE LOGITS
     default
    0.48
     sigmoid
    0.47
     fries
    0.43
    再度
    0.43
     normally
    0.42
     Heisenberg
    0.42
     median
    0.42
     gener
    0.42
     passag
    0.41
     cov
    0.41
    Activations Density 0.000%

    No Known Activations