© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12677
    Prev
    Next
    INDEX
    Explanations

    while supplies last or as long as

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

    while loop conditions

    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
     konst
    0.41
     idx
    0.41
     TVs
    0.40
     телевиде
    0.40
     HDTV
    0.40
     selectable
    0.40
     quà
    0.40
    ￳
    0.40
    Œ
    0.39
     Tada
    0.39
    POSITIVE LOGITS
     ድረስ
    0.51
    仍然
    0.50
     until
    0.48
    still
    0.48
    还有
    0.48
    keep
    0.47
     Until
    0.46
     still
    0.46
    Master
    0.45
    Until
    0.45
    Activations Density 0.030%

    No Known Activations