© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 101824
    Prev
    Next
    INDEX
    Explanations

    taxable income

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    楞
    0.39
     hormonal
    0.39
     genotype
    0.38
     EDTA
    0.37
    ⊤
    0.37
    ulfite
    0.37
    侣
    0.37
     পার
    0.37
     QTL
    0.36
     кисло
    0.36
    POSITIVE LOGITS
    伝説
    0.43
    Zara
    0.39
    今年も
    0.38
    stitches
    0.38
    Beans
    0.37
    แย
    0.37
    single
    0.37
     yks
    0.37
    箅
    0.37
    vintage
    0.37
    Activations Density 0.082%

    No Known Activations