© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 133690
    Prev
    Next
    INDEX
    Explanations

    weather, removal, fans

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

    container and layout centering

    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
     ရှိ
    0.63
     bộ
    0.58
     trộn
    0.55
     chúc
    0.54
     houden
    0.53
     ConcurrentTask
    0.53
    鐩
    0.52
     dùng
    0.51
     núi
    0.51
     slat
    0.51
    POSITIVE LOGITS
    f
    0.57
    ф
    0.55
    м
    0.54
    ar
    0.54
    л
    0.53
    к
    0.52
    0
    0.52
    Respons
    0.51
    Ung
    0.51
    m
    0.51
    Activations Density 0.000%

    No Known Activations