© 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. 7322
    Prev
    Next
    INDEX
    Explanations

    nuclear physics

    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
    ية
    2.47
    ৯
    2.27
    ز
    2.02
    ным
    1.95
    ৭
    1.87
    يك
    1.86
    ৫
    1.82
    ました
    1.78
    ный
    1.77
    ่า
    1.77
    POSITIVE LOGITS
     γιατί
    1.80
    реди
    1.71
    데이
    1.71
    矣
    1.71
    uh
    1.69
     причина
    1.68
     základě
    1.67
    大致
    1.64
    地的
    1.63
     dû
    1.63
    Activations Density 0.005%

    No Known Activations