© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1121
    Prev
    Next
    INDEX
    Explanations

    URLs and informational websites

    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
    者が
    1.48
    杀了
    1.37
     λό
    1.37
     objs
    1.36
    人员
    1.36
     newTask
    1.35
    흘
    1.34
     elapsedTime
    1.33
    ﻠ
    1.33
     local
    1.32
    POSITIVE LOGITS
    ország
    1.62
     Selatan
    1.51
    issance
    1.44
    ğı
    1.44
    ische
    1.43
    🇹
    1.43
    iche
    1.39
    konstru
    1.39
    pean
    1.38
    Bel
    1.37
    Activations Density 0.632%

    No Known Activations