© 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. 146521
    Prev
    Next
    INDEX
    Explanations

    scheduling and largest cities

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

    modern plumbing and sanitation

    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
     wilayah
    0.50
    ólicos
    0.50
     Mekong
    0.50
    =",
    0.49
    ाइ
    0.49
    unjukan
    0.49
    productive
    0.48
    asiswa
    0.48
    atia
    0.47
    hills
    0.47
    POSITIVE LOGITS
    աղ
    0.50
    きました
    0.45
    տ
    0.45
    ոչ
    0.45
    CRT
    0.44
     createTask
    0.43
     setCount
    0.43
    作った
    0.43
    ரு
    0.42
    次
    0.42
    Activations Density 0.001%

    No Known Activations