© 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. 5511
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in contexts

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

    numbers and mathematical expressions

    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
     दुसरे
    0.41
    োপাধ্যা
    0.38
    ObjectTemp
    0.37
     niekoľ
    0.36
     ಹಲವಾರು
    0.36
     ٻ
    0.36
    ᒎ
    0.35
     $\{\
    0.35
     déprimées
    0.34
     mehreren
    0.34
    POSITIVE LOGITS
    ′
    1.28
    ″
    1.24
    ️⃣
    1.20
    ⃣
    1.10
    ′,
    1.06
    ½
    0.79
    %
    0.74
    th
    0.71
    +
    0.69
    ′-
    0.68
    Activations Density 0.278%

    No Known Activations