© 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. 9835
    Prev
    Next
    INDEX
    Explanations

    income tax forms

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

    tax forms 1099 W-2 ITIN

    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
    सोई
    0.48
    като
    0.47
    supportsFocus
    0.47
    ụng
    0.46
     अटैक
    0.45
    кован
    0.45
    暝
    0.45
    ⭒
    0.44
    欹
    0.43
    ани
    0.43
    POSITIVE LOGITS
     carol
    0.47
     kalau
    0.44
     Fifty
    0.43
     EE
    0.42
     ys
    0.42
     haven
    0.42
     pagare
    0.42
     siano
    0.42
     aa
    0.41
     furono
    0.41
    Activations Density 0.006%

    No Known Activations