© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 138603
    Prev
    Next
    INDEX
    Explanations

    US Treasury Department or Secretary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     처리
    0.77
    tois
    0.73
    opard
    0.67
    toDouble
    0.65
    嫖
    0.63
     되고
    0.63
     وتن
    0.63
    ked
    0.62
    endien
    0.62
    hotra
    0.62
    POSITIVE LOGITS
     as
    1.05
    k
    0.94
    ad
    0.91
    સ
    0.89
    ન
    0.86
    મ
    0.85
     a
    0.83
     acids
    0.83
    یت
    0.82
    n
    0.81
    Activations Density 0.001%

    No Known Activations