© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1722
    Prev
    Next
    INDEX
    Explanations

    position relative;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_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
     memorize
    0.97
     preamble
    0.91
     renormal
    0.87
     preface
    0.86
     hypergeometric
    0.85
    ু
    0.84
     phrasing
    0.84
    ರುತ್ತದೆ
    0.83
    誹
    0.83
     moth
    0.82
    POSITIVE LOGITS
    ق
    1.03
     Jefe
    0.97
    zig
    0.95
    حسن
    0.94
    icked
    0.92
     Vorsitz
    0.92
     heureux
    0.91
    ح
    0.91
    Bounds
    0.89
    folios
    0.86
    Activations Density 0.001%

    No Known Activations