© 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. 90309
    Prev
    Next
    INDEX
    Explanations

    flights, meals, lace

    np_acts-logits-general · gemini-2.5-flash-lite

    QR codes and eSIMs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     moulds
    0.49
     मंगल
    0.49
     метода
    0.48
     ..............
    0.47
    ➰
    0.47
     साह
    0.47
    ---------------
    0.46
    বাবুর
    0.46
    ıyordu
    0.46
    ästä
    0.46
    POSITIVE LOGITS
    ប់
    0.46
    sap
    0.44
    trigger
    0.44
     rých
    0.44
     Holocaust
    0.43
    ↵↵
    0.43
    oare
    0.42
    zed
    0.42
    rzym
    0.42
    alth
    0.42
    Activations Density 0.000%

    No Known Activations