© 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. 12346
    Prev
    Next
    INDEX
    Explanations

    benchmark"}, "хоро" followed by {"шему"}.There are many occurrences related to "benchmark" and " хоро" (which means "good" or "well" in Russian, often used in phrases like "по-хорошему" meaning "in a good way" or "amicably").benchmark, хоро

    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
     matriline
    0.84
    tection
    0.82
    ら
    0.82
     Numerous
    0.81
     tuberc
    0.80
    লি
    0.79
     diel
    0.79
     वेग
    0.79
     Verein
    0.79
     Systematic
    0.77
    POSITIVE LOGITS
    헴
    0.91
    лығы
    0.87
    )\}$
    0.82
    하게
    0.80
    Қ
    0.80
    )\}
    0.78
    ).]
    0.78
    ਤੀ
    0.77
    어를
    0.76
    $.)
    0.75
    Activations Density 0.000%

    No Known Activations