© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1821
    Prev
    Next
    INDEX
    Explanations

    `while` loop conditions in code

    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_13_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
      
    1.16
    q
    0.95
    pas
    0.94
    iv
    0.93
    f
    0.93
    p
    0.93
    pa
    0.89
    ı
    0.87
    d
    0.86
    str
    0.85
    POSITIVE LOGITS
    <unused908>
    1.64
     모르
    1.63
    <unused891>
    1.62
    <unused1179>
    1.55
    <unused949>
    1.55
    <unused1174>
    1.55
    <unused466>
    1.55
     manifestly
    1.54
    <unused1182>
    1.53
    <unused942>
    1.53
    Activations Density 0.006%

    No Known Activations