© 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-262K
    7. 694
    Prev
    Next
    INDEX
    Explanations

    numbers followed by gram

    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_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
    1
    0.41
     quantités
    0.36
     dioxide
    0.35
    0
    0.34
     pequeños
    0.34
     quarts
    0.34
    iseen
    0.34
     dozen
    0.34
    ushing
    0.34
     liters
    0.34
    POSITIVE LOGITS
    ह
    0.42
    inicio
    0.37
    ว่า
    0.37
    ວ່າ
    0.36
    ను
    0.36
    MyToolkit
    0.35
    פה
    0.35
     Nava
    0.35
    но
    0.34
    }")
    0.33
    Activations Density 0.000%

    No Known Activations