© 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. 7941
    Prev
    Next
    INDEX
    Explanations

    chicken or the egg

    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
     রহিয়াছে
    1.65
     !!!!!
    1.54
     Thereby
    1.53
     !!!!
    1.52
     সম্পূর্ন
    1.49
     ;-
    1.43
    ZrO
    1.43
    。。。。
    1.42
     !!,
    1.40
     !!!
    1.40
    POSITIVE LOGITS
     or
    1.34
     page
    1.09
     página
    1.01
    or
    0.97
     navigating
    0.97
     the
    0.97
    —
    0.95
    -
    0.94
    page
    0.89
    ↵
    0.88
    Activations Density 0.001%

    No Known Activations