© 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. 253753
    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
     predicates
    0.50
     germanium
    0.49
     ovlád
    0.48
     وأ
    0.47
     bunkers
    0.47
     vultures
    0.47
     predicate
    0.46
     አ
    0.45
     encoders
    0.45
     infrastructures
    0.45
    POSITIVE LOGITS
    一方で
    0.47
    webview
    0.47
     compartir
    0.47
    拼
    0.46
    ของการ
    0.45
    ร้อน
    0.45
    一方
    0.44
    *}{
    0.44
    多次
    0.43
    共享
    0.43
    Activations Density 0.001%

    No Known Activations