© 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. 68191
    Prev
    Next
    INDEX
    Explanations

    with us

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

    grand duchy, capital, price

    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
    遒
    0.38
    Ᏸ
    0.38
    šte
    0.38
     materially
    0.38
    岗位
    0.38
    ⏤
    0.38
    旨在
    0.37
     lenses
    0.37
     crucially
    0.37
    但这
    0.37
    POSITIVE LOGITS
     erstellt
    0.48
     bekommen
    0.47
     aidant
    0.44
     UPDATE
    0.43
     bombarded
    0.42
    demo
    0.41
     inundated
    0.40
    ଘ
    0.40
     vimos
    0.39
     snatched
    0.39
    Activations Density 0.002%

    No Known Activations