© 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. 184058
    Prev
    Next
    INDEX
    Explanations

    applied to or related to tax

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

    LLMs parameters

    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
    anggap
    0.54
    équip
    0.50
    어를
    0.48
    ान्य
    0.45
    razia
    0.45
    짠
    0.45
    ств
    0.44
    discrimination
    0.44
    꼬
    0.43
    诏
    0.43
    POSITIVE LOGITS
     Christmas
    0.57
     Hillary
    0.46
     Fukushima
    0.46
     Weihnacht
    0.46
     recalculated
    0.44
     FTX
    0.44
     Dunham
    0.44
     café
    0.44
     proudly
    0.43
     Weihnachts
    0.43
    Activations Density 0.000%

    No Known Activations