© 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. 702
    Prev
    Next
    INDEX
    Explanations

    mathematical formatting and symbols

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

    multiplication or division symbols

    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
    这场
    0.23
    什么样的
    0.22
    GoAbroad
    0.21
    重视
    0.21
    财政
    0.20
    话题
    0.20
    决心
    0.20
    军
    0.20
    waitForIdleSync
    0.20
     meticulously
    0.20
    POSITIVE LOGITS
    mi
    0.33
    mtext
    0.26
    mo
    0.25
    msup
    0.25
     cdot
    0.24
    mathrm
    0.23
    msub
    0.23
    mspace
    0.22
     x
    0.22
    mfenced
    0.22
    Activations Density 0.028%

    No Known Activations