© 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. 50475
    Prev
    Next
    INDEX
    Explanations

    taxation and related financial terms

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

    tax implications, invoice, rate, etc

    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
    ियों
    0.70
     predominant
    0.69
     thatched
    0.69
     bequeathed
    0.69
     swayed
    0.67
     confided
    0.66
    т
    0.66
     flocked
    0.66
     stabbed
    0.64
    ির
    0.64
    POSITIVE LOGITS
     as
    0.80
    ล
    0.79
    o
    0.72
    ट
    0.70
    ם
    0.70
    ны
    0.70
    ד
    0.69
    Tax
    0.68
    as
    0.67
    ↵↵
    0.66
    Activations Density 0.021%

    No Known Activations