© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10012
    Prev
    Next
    INDEX
    Explanations

    shape language

    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
    ি
    1.88
    ु
    1.88
    𝗴
    1.79
     Argu
    1.66
    ों
    1.59
     Estr
    1.59
    υ
    1.56
     Customizable
    1.55
    ມ
    1.52
    ы
    1.52
    POSITIVE LOGITS
     designado
    2.39
     tiende
    2.33
    浯
    2.33
    ยนต์
    2.30
    ის
    2.25
     manifiesta
    2.09
    ాన్ని
    2.08
    اد
    2.05
    ية
    2.05
     pulgadas
    2.05
    Activations Density 0.021%

    No Known Activations