© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31852
    Prev
    Next
    INDEX
    Explanations

    períodicos.com

    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_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
    shoot
    1.45
    li
    1.41
    shirts
    1.38
    我
    1.33
    sliders
    1.32
    ъ
    1.32
    shots
    1.30
    ே
    1.30
    sparse
    1.27
    те
    1.27
    POSITIVE LOGITS
    ت
    1.98
    ن
    1.58
    Κ
    1.46
    ﺪ
    1.45
    އ
    1.43
     поколения
    1.41
    ను
    1.39
    不用
    1.39
    נ
    1.38
    ج
    1.37
    Activations Density 0.001%

    No Known Activations