© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8713
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical operations

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

    numbers and arithmetic operations

    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
     NORMAL
    0.44
    NORMAL
    0.44
    ו
    0.42
    éo
    0.41
    adie
    0.39
     ገን
    0.38
    normal
    0.38
    боль
    0.38
    fyp
    0.38
    chuk
    0.38
    POSITIVE LOGITS
     !=
    0.42
     +=
    0.42
     }}=\
    0.41
    Equals
    0.40
    \|_{\
    0.40
     πρώτη
    0.39
     inhibitory
    0.39
    しております
    0.39
     fórmulas
    0.38
     getText
    0.38
    Activations Density 0.004%

    No Known Activations