© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1851
    Prev
    Next
    INDEX
    Explanations

    squaring and exponents

    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/layer_40_width_65k_l0_medium
    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
    ゾート
    0.46
    cooler
    0.39
    ชาย
    0.39
    обходимо
    0.39
     commotion
    0.39
    ⣿
    0.39
    letown
    0.38
    ığınız
    0.38
    ⤥
    0.38
    icama
    0.38
    POSITIVE LOGITS
     squared
    0.86
    squared
    0.78
    ²
    0.78
    ²,
    0.77
    ^{
    0.75
    ^
    0.69
    ².
    0.68
     제곱
    0.64
     exponent
    0.63
     Squared
    0.63
    Activations Density 0.109%

    No Known Activations