© 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. 31-GEMMASCOPE-2-RES-16K
    4. 16221
    Prev
    Next
    INDEX
    Explanations

    called after "oko"

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

    is **

    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_31_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
     രണ്ട്
    0.49
    wania
    0.47
     wellknown
    0.45
    ၣ်
    0.44
     three
    0.44
    aditional
    0.44
    .​​
    0.43
     இரண்டு
    0.42
     गौरतलब
    0.42
     two
    0.42
    POSITIVE LOGITS
    <b>
    0.94
    <strong>
    0.89
     %``
    0.72
    『
    0.61
    ॒
    0.60
    <code>
    0.59
     
    0.58
    <i>
    0.56
    《
    0.56
     **
    0.55
    Activations Density 0.543%

    No Known Activations