© 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. 86050
    Prev
    Next
    INDEX
    Explanations

    tax and cryptocurrency income/wealth

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

    sanctions and regulations

    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
    輕鬆
    0.42
     ಕನ್ನಡ
    0.42
     ਪਰ
    0.41
     walnut
    0.40
     footprint
    0.40
     سلام
    0.40
     '**
    0.39
     forgetting
    0.38
     shay
    0.38
    ნიშვნელ
    0.38
    POSITIVE LOGITS
     উপার্জন
    0.44
    StartZ
    0.42
    ខ្សែ
    0.41
     CI
    0.39
    DX
    0.39
    Pixels
    0.38
    miy
    0.38
    ឆ្នាំ
    0.37
    风
    0.37
     फंडा
    0.37
    Activations Density 0.007%

    No Known Activations