© 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. 159388
    Prev
    Next
    INDEX
    Explanations

    financial district apartments or push piers

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

    tackle Maryland

    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
    紆
    0.50
     allocating
    0.49
    erful
    0.45
    द
    0.44
    ਸ਼
    0.41
    噼
    0.41
     appointing
    0.41
    лянчук
    0.41
    ర
    0.41
     उठाकर
    0.41
    POSITIVE LOGITS
     jossa
    0.52
    ্যাট
    0.51
     dizer
    0.50
     traiter
    0.50
    |"
    0.50
    rivez
    0.48
    ENSION
    0.48
     brands
    0.48
     renders
    0.48
    éments
    0.48
    Activations Density 0.001%

    No Known Activations