© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1358
    Prev
    Next
    INDEX
    Explanations

    compounding interest

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

    frequency and rates

    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
    ätta
    0.41
    桩
    0.40
    NewDecoder
    0.38
    ছিলেন
    0.38
    锴
    0.37
    Surname
    0.36
    keley
    0.36
    莧
    0.36
    ळक
    0.35
    各种
    0.35
    POSITIVE LOGITS
     compounding
    1.39
     compounded
    1.19
     compound
    1.02
     periods
    1.02
     compounds
    0.98
     Compound
    0.98
     Compounds
    0.97
     Periods
    0.97
    compound
    0.95
     COMPOUNDS
    0.95
    Activations Density 0.004%

    No Known Activations