© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1233
    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_31_width_16k_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
     সবচে
    0.59
     উদ্দেশে
    0.59
    ぞれ
    0.57
    要有
    0.57
    かな
    0.56
    必要があります
    0.56
    我也是
    0.56
    須
    0.56
    ेष
    0.55
    まだ
    0.55
    POSITIVE LOGITS
     helps
    2.91
     allows
    2.84
     enables
    2.75
     ensures
    2.63
     позволяет
    2.50
     gives
    2.47
     помогает
    2.42
     pozwala
    2.41
     prevents
    2.39
     Allows
    2.39
    Activations Density 1.131%

    No Known Activations