© 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. 112855
    Prev
    Next
    INDEX
    Explanations

    individual parts or members

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

    no memory

    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
    ↵
    0.47
     gc
    0.47
    rade
    0.44
     GC
    0.43
     be
    0.42
     lf
    0.42
    惑
    0.42
    트
    0.42
    {
    0.41
    爾
    0.41
    POSITIVE LOGITS
    ându
    0.67
     فترة
    0.49
    AppBsky
    0.49
     філь
    0.48
    aways
    0.48
    UtcNow
    0.48
    מ
    0.47
    iliśmy
    0.47
     trajectories
    0.47
    noz
    0.46
    Activations Density 0.001%

    No Known Activations