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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14571
    Prev
    Next
    INDEX
    Explanations

    O(n^2) complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    -​
    1.31
     sóc
    1.31
    ٔ
    1.30
     Ums
    1.29
     tiên
    1.28
     xu
    1.27
     quát
    1.26
    ​
    1.26
    Interpolator
    1.25
     Senhor
    1.24
    POSITIVE LOGITS
    <unused360>
    1.63
    vdd
    1.62
    <unused106>
    1.60
     এডিনবার্গ
    1.60
    LLDB
    1.59
     पैकिंग
    1.57
     pabc
    1.56
     نړۍ
    1.55
     atthakath
    1.53
    asaddo
    1.52
    Activations Density 0.012%

    No Known Activations