© 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. 159903
    Prev
    Next
    INDEX
    Explanations

    IRS tax

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

    observations

    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
    挨
    0.50
     oldal
    0.49
    进攻
    0.47
    𝐥
    0.46
     arrivare
    0.45
     ennemis
    0.45
    inine
    0.45
    壮
    0.45
    日益
    0.44
    bz
    0.43
    POSITIVE LOGITS
     meiosis
    0.50
     Gen
    0.48
     теорети
    0.48
     catechol
    0.47
     dioc
    0.47
     thermost
    0.47
     Gamb
    0.46
     Inferno
    0.46
     surfing
    0.46
     LOOK
    0.46
    Activations Density 0.000%

    No Known Activations