© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1493
    Prev
    Next
    INDEX
    Explanations

    Slavic languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
     údaje
    0.37
     величина
    0.36
     устройство
    0.34
     мощность
    0.34
     У
    0.33
     По
    0.33
    струк
    0.33
     отдельные
    0.33
    сна
    0.33
     у
    0.33
    POSITIVE LOGITS
     dulces
    0.51
     coinvol
    0.46
     பட்ட
    0.43
     humild
    0.40
     apoy
    0.40
    甘
    0.40
    蜜
    0.38
    真心
    0.38
    温暖
    0.38
     pension
    0.38
    Activations Density 0.006%

    No Known Activations