© 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-262K
    7. 11412
    Prev
    Next
    INDEX
    Explanations

    loop and conditional termination

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

    exiting loops

    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_262k_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
    של
    0.42
    AJ
    0.42
    꺾
    0.42
    ovou
    0.42
    াক্ত
    0.41
    Atl
    0.40
     Его
    0.40
    He
    0.40
    ዜ
    0.40
    canoe
    0.39
    POSITIVE LOGITS
     sonst
    0.48
     resorts
    0.47
     Worst
    0.46
     otherwise
    0.46
     Resort
    0.44
    дентификаторы
    0.43
     enormes
    0.43
     resorted
    0.42
    探し
    0.41
     Resorts
    0.41
    Activations Density 0.000%

    No Known Activations