© 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. 89415
    Prev
    Next
    INDEX
    Explanations

    stamp duty

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

    Brazilian markets

    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
    НА
    0.51
    现代
    0.48
    k
    0.47
    ColumnHeaders
    0.46
    Handling
    0.46
    ন
    0.45
    NA
    0.45
    studies
    0.44
    VD
    0.44
    Corporate
    0.44
    POSITIVE LOGITS
     lista
    0.50
     genital
    0.48
     centimet
    0.47
     Tanzania
    0.47
     vagina
    0.46
    ئة
    0.46
    炫
    0.46
     aquela
    0.46
     uitle
    0.46
     quella
    0.44
    Activations Density 0.000%

    No Known Activations