© 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. 259542
    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
    똘
    0.47
     licz
    0.46
    鳞
    0.43
    WCHAR
    0.43
    ISTAN
    0.42
    তিতে
    0.42
     pendapat
    0.42
    FORM
    0.41
    CHARACTER
    0.41
    াদার
    0.41
    POSITIVE LOGITS
     أنها
    0.47
     Диа
    0.47
    管
    0.47
     Accountant
    0.46
     Logistics
    0.46
    កំណត់
    0.45
     Logistic
    0.45
     Она
    0.43
    πό
    0.43
    elry
    0.43
    Activations Density 0.001%

    No Known Activations