© 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. 5667
    Prev
    Next
    INDEX
    Explanations

    sexual, space, moral, quantum, optimization, advertising, data, energy, commerce

    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
    ↵↵
    1.50
    am
    1.13
    ak
    1.04
    is
    1.01
    ↵
    0.96
    K
    0.96
    at
    0.94
    0
    0.91
    M
    0.89
    H
    0.88
    POSITIVE LOGITS
     а
    1.03
     a
    0.93
    ُر
    0.91
    বিভিন্ন
    0.90
     and
    0.88
     нескольких
    0.87
    𝑢
    0.87
     மற்றும்
    0.86
    এবং
    0.85
    odial
    0.85
    Activations Density 1.354%

    No Known Activations