© 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. 5403
    Prev
    Next
    INDEX
    Explanations

    PowerPoint presentation

    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
    т
    1.56
    ع
    1.51
    ע
    1.48
    с
    1.41
    פ
    1.37
    о
    1.33
    <0xA0>
    1.26
    0
    1.26
     Эта
    1.23
     Ее
    1.23
    POSITIVE LOGITS
    slide
    1.34
    slides
    1.32
    XPath
    1.32
    he
    1.23
    あった
    1.23
    irtschaft
    1.22
    ചര്യ
    1.22
    ளில்
    1.20
    하시는
    1.20
    طور
    1.20
    Activations Density 0.006%

    No Known Activations