© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10947
    Prev
    Next
    INDEX
    Explanations

    pronoun references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
     شپ
    0.41
    慜
    0.40
    最后
    0.39
    ём
    0.39
    。
    0.39
    电话
    0.37
    вра
    0.37
    연
    0.36
    パン
    0.36
    远
    0.35
    POSITIVE LOGITS
    ಂಗ್
    0.43
     kült
    0.42
     confocal
    0.42
     çap
    0.41
     plastik
    0.40
     inov
    0.39
     değiştir
    0.38
     uso
    0.38
     tarih
    0.38
     ساخته
    0.38
    Activations Density 0.019%

    No Known Activations