© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 496
    Prev
    Next
    INDEX
    Explanations

    compound interest

    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_53_width_65k_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
    䂙
    0.34
     étro
    0.34
    ങ്ക്
    0.33
    𐰣
    0.33
    兟
    0.31
    ब्रेरी
    0.31
    架构
    0.30
    লিখ
    0.30
    笊
    0.30
    ্পর্শ
    0.30
    POSITIVE LOGITS
     compound
    0.75
     compounding
    0.75
     Compound
    0.72
    compound
    0.69
     compounded
    0.68
     कंपाउंड
    0.65
    Compound
    0.63
     compounds
    0.59
     COMPO
    0.52
     Compounds
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.