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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 16853
    Prev
    Next
    INDEX
    Explanations

    polynomials and mathematical curves

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

    polynomial equations

    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
    大人
    0.45
    早餐
    0.44
    军事
    0.42
    诉
    0.42
    蝰
    0.40
    訫
    0.39
    姑娘
    0.39
    脱
    0.39
    閘
    0.38
    মধ
    0.38
    POSITIVE LOGITS
     polynomial
    3.11
     Polynomial
    3.02
     polynomials
    3.00
    polynomial
    2.95
    Polynomial
    2.86
     polinom
    2.41
     polinomio
    2.36
     polynom
    2.36
     polyn
    2.34
     polin
    2.25
    Activations Density 0.017%

    No Known Activations