© 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. 228489
    Prev
    Next
    INDEX
    Explanations

    legal and contractual phrases

    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
    fueled
    0.57
    しますが
    0.54
     Landscapes
    0.52
    ometimes
    0.49
    SETS
    0.47
    ီ
    0.47
    公園
    0.46
    这
    0.46
    often
    0.46
    搶
    0.46
    POSITIVE LOGITS
     calific
    0.48
     charla
    0.48
     realmente
    0.46
    PopupMenu
    0.45
    yect
    0.43
     misma
    0.43
    Datos
    0.43
     reporte
    0.42
     mismas
    0.42
    irá
    0.42
    Activations Density 0.000%

    No Known Activations