© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35521
    Prev
    Next
    INDEX
    Explanations

    essays

    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
    ek
    2.30
    ا
    2.13
    ف
    1.76
    মহাদেশ
    1.74
    enzie
    1.72
     явля
    1.67
    å
    1.66
    تی
    1.65
     solcher
    1.65
     tribun
    1.63
    POSITIVE LOGITS
    ри
    2.14
    ный
    1.89
    ной
    1.83
    듬
    1.83
    regation
    1.76
     Само
    1.68
    ных
    1.67
    ų
    1.65
     dearly
    1.62
    ер
    1.61
    Activations Density 0.005%

    No Known Activations