© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2170
    Prev
    Next
    INDEX
    Explanations

    math and academic subjects

    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_24_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
    𝚗
    0.75
    でしたが
    0.69
    初始化
    0.67
    ූර්
    0.64
    䂘
    0.64
    Garage
    0.63
     dwóch
    0.63
    コントロール
    0.63
     configuring
    0.62
    しましたが
    0.61
    POSITIVE LOGITS
     Algebra
    0.75
     Textbook
    0.70
     Olympi
    0.68
    ™
    0.65
     ·
    0.62
     Essay
    0.62
     একাডেমিক
    0.61
     Ace
    0.59
     Euclid
    0.59
     |
    0.58
    Activations Density 0.015%

    No Known Activations