© 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. 10027
    Prev
    Next
    INDEX
    Explanations

    breaking out of loops

    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
     maka
    0.98
    中华人民共和国
    0.97
     형태로
    0.92
     dopln
    0.91
    (**
    0.90
     অধিকারী
    0.89
     culturali
    0.87
     spoloč
    0.86
    பின்னர்
    0.86
    發展
    0.86
    POSITIVE LOGITS
    ↵↵
    1.00
     Refriger
    1.00
     Ramen
    0.99
    还没有
    0.98
     Titanium
    0.98
     verloren
    0.96
     هنوز
    0.95
     Flax
    0.95
    Tabuleiro
    0.95
     todavía
    0.94
    Activations Density 0.021%

    No Known Activations