© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4332
    Prev
    Next
    INDEX
    Explanations

    PE = m * g * h

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "*");
    0.80
    ността
    0.79
     ただ
    0.75
     astfel
    0.75
    ку
    0.74
     informational
    0.74
    шению
    0.73
     இதுபோன்ற
    0.73
     ибо
    0.73
     बरत
    0.73
    POSITIVE LOGITS
    ก
    0.77
    Clin
    0.73
     jerseys
    0.73
     Roca
    0.73
    Rock
    0.70
    Reaction
    0.69
    Protein
    0.68
     Reforms
    0.68
    ូង
    0.68
    ప్ప
    0.67
    Activations Density 0.000%

    No Known Activations