© 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-262K
    7. 35025
    Prev
    Next
    INDEX
    Explanations

    investment in

    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
    ു
    0.79
    ナソニック
    0.77
     лишь
    0.76
     plena
    0.76
     стекла
    0.76
    𝗌
    0.75
     многочис
    0.73
     пришлось
    0.73
    ровать
    0.73
     инициа
    0.73
    POSITIVE LOGITS
    傩
    0.75
     sebuah
    0.75
     Methodology
    0.75
     Sebuah
    0.74
     datang
    0.73
     bukti
    0.71
     diterapkan
    0.71
    nya
    0.71
    的作品
    0.69
     Lectures
    0.68
    Activations Density 0.000%

    No Known Activations