© 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. 260067
    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
    Pers
    0.46
    র্ষি
    0.46
    {})
    0.45
    __()
    0.45
    what
    0.42
    raff
    0.42
    ")
    0.41
    plied
    0.41
    ‎
    0.41
     "")
    0.41
    POSITIVE LOGITS
     وصول
    0.55
     அமைந்துள்ள
    0.50
     моих
    0.50
     становника
    0.50
     ühe
    0.50
     négl
    0.50
     tı
    0.49
     這個
    0.48
     ನನ್ನ
    0.48
     މަ
    0.48
    Activations Density 0.000%

    No Known Activations