© 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. 260194
    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
     ἐ
    0.56
     develops
    0.54
     sportive
    0.53
     hemicontinuous
    0.52
     εἰ
    0.52
     postgraduate
    0.51
     wretched
    0.50
     depressive
    0.50
     understands
    0.49
     පො
    0.49
    POSITIVE LOGITS
    Y
    0.54
    ANK
    0.49
    АН
    0.48
    Purch
    0.48
    Ы
    0.47
    ge
    0.47
    Property
    0.47
    Ton
    0.46
    IG
    0.46
    Buyers
    0.46
    Activations Density 0.001%

    No Known Activations