© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 5567
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     and
    1.26
     Ceres
    1.25
    思う
    1.23
    𝖊
    1.16
     i
    1.16
    க
    1.16
    𝐓
    1.16
    𝖆
    1.16
    𝖎
    1.13
     the
    1.12
    POSITIVE LOGITS
    ا
    1.87
    น
    1.79
    EndGlobalSection
    1.66
    та
    1.59
    ان
    1.59
    ia
    1.59
    нің
    1.58
     permitió
    1.57
    GlobalSection
    1.52
    น้อง
    1.52
    Activations Density 2.292%

    No Known Activations