© 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. 45117
    Prev
    Next
    INDEX
    Explanations

    desktop computers

    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
    gie
    2.23
    gem
    1.63
    ありません
    1.62
    goers
    1.59
    mente
    1.56
    쏙
    1.55
    gers
    1.52
    staande
    1.50
    cap
    1.48
    glycos
    1.48
    POSITIVE LOGITS
    м
    2.05
    م
    2.05
    ين
    1.95
    ни
    1.92
    ל
    1.80
    ž
    1.73
    ू
    1.72
     iguales
    1.70
    il
    1.63
    ிறது
    1.61
    Activations Density 0.004%

    No Known Activations