© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5585
    Prev
    Next
    INDEX
    Explanations

    Midjourney, Maps, Karnaugh

    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
    ﺭ
    1.05
    ﻭ
    1.04
     jotka
    1.02
    ть
    1.02
    的時候
    1.02
    দিন
    0.99
    ти
    0.93
    ﺩ
    0.91
    iorari
    0.90
    цца
    0.88
    POSITIVE LOGITS
    ين
    1.50
    ів
    1.31
    اب
    1.17
    ε
    1.16
    ون
    1.14
    punkt
    1.11
    ій
    1.10
    েরই
    1.05
    ું
    1.04
    իկ
    1.04
    Activations Density 0.075%

    No Known Activations