© 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. 5193
    Prev
    Next
    INDEX
    Explanations

    mid-level languages, automatic weapon, government-sponsored enterprises, special process, terminate and stay resident

    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
    可以
    2.17
    하고
    1.84
    不懂
    1.84
    ৩
    1.84
    입니다
    1.79
    不愿意
    1.76
    할
    1.75
    คุณ
    1.70
    이다
    1.69
    不够
    1.69
    POSITIVE LOGITS
    1
    1.71
    ro
    1.53
    sw
    1.52
    Algorithms
    1.50
    sk
    1.45
    That
    1.45
    THE
    1.45
    surprise
    1.41
     Gandhiji
    1.41
    The
    1.40
    Activations Density 0.000%

    No Known Activations