© 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. 256489
    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
    原来
    0.48
     mieszkań
    0.48
    Δ
    0.46
     desplazamiento
    0.44
    م
    0.44
    α
    0.43
    原
    0.43
    我在
    0.42
    ابعة
    0.42
    ون
    0.42
    POSITIVE LOGITS
     खोसला
    0.61
     टूर्
    0.56
     みたい
    0.54
     ရှိ
    0.52
    ṛ
    0.51
    fellow
    0.50
     Qxe
    0.49
     போது
    0.49
    passt
    0.49
     वीजा
    0.49
    Activations Density 0.001%

    No Known Activations