© 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. 187376
    Prev
    Next
    INDEX
    Explanations

    convergence of ideas

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

    differences and nuances

    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
    サラダ
    0.52
    ุน
    0.52
    drying
    0.52
    anhyd
    0.50
    ૅ
    0.49
    د
    0.49
    ہری
    0.48
    donut
    0.48
    èg
    0.47
    もちろん
    0.47
    POSITIVE LOGITS
    :
    0.59
     take
    0.52
     Victor
    0.50
     Car
    0.47
     Mej
    0.47
     J
    0.47
     Friend
    0.47
     Ada
    0.47
     Leah
    0.46
     Morgan
    0.45
    Activations Density 0.000%

    No Known Activations