© 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. 68746
    Prev
    Next
    INDEX
    Explanations

    Federal Reserve quantitative easing

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

    financial reserve assets

    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
    स्थित
    0.50
    烃
    0.48
    lich
    0.45
     lich
    0.44
     leer
    0.43
    爆
    0.42
    IDAY
    0.42
    烈
    0.41
    亢
    0.41
    殺
    0.41
    POSITIVE LOGITS
     grandparents
    0.46
     సే
    0.46
     dieting
    0.46
    otropic
    0.45
     stretching
    0.45
     nên
    0.44
     mothers
    0.44
     scavenging
    0.44
     heartfelt
    0.44
     motto
    0.43
    Activations Density 0.002%

    No Known Activations