© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 259366
    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
    oauth
    0.50
     quartile
    0.50
     καθη
    0.49
     ধাত
    0.48
     )$
    0.47
     ব্যতীত
    0.46
    ),]$
    0.44
     дори
    0.44
    )")
    0.44
     gấp
    0.44
    POSITIVE LOGITS
     underworld
    0.48
    이는
    0.46
    حات
    0.45
    حمد
    0.44
    今
    0.44
     meshes
    0.43
     rmg
    0.42
     będzie
    0.42
     istnieje
    0.42
    酒店
    0.42
    Activations Density 0.001%

    No Known Activations