© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252265
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     不需要
    0.50
    幢
    0.47
    離婚
    0.46
     inefficiencies
    0.45
    含有
    0.44
    قاء
    0.44
    䏍
    0.44
    會有
    0.44
     adultery
    0.44
    是不
    0.44
    POSITIVE LOGITS
     épa
    0.52
     Baş
    0.50
     Yardım
    0.46
    Baş
    0.46
    骥
    0.45
     پیسې
    0.44
     dvě
    0.44
     Repubblica
    0.43
    şağı
    0.43
     część
    0.42
    Activations Density 0.000%

    No Known Activations