© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1099
    Prev
    Next
    INDEX
    Explanations

    compound interest and compounding

    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
    arranty
    0.46
    ृति
    0.43
    ഗത
    0.42
    Warranty
    0.42
    Ꮈ
    0.42
    withtag
    0.42
    朹
    0.42
    ̉i
    0.39
    ریق
    0.39
    定时
    0.39
    POSITIVE LOGITS
     compound
    3.31
     Compound
    3.09
    Compound
    2.97
     compounding
    2.95
    compound
    2.92
     compounded
    2.88
     compounds
    2.64
     Compounds
    2.53
     कंपाउंड
    2.44
     COMPO
    2.39
    Activations Density 0.008%

    No Known Activations