© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1804
    Prev
    Next
    INDEX
    Explanations

    beginning to end

    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_17_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
     sacrificing
    0.88
    麾
    0.85
    愧
    0.83
    oulos
    0.82
     affixed
    0.78
    旗下
    0.77
    idge
    0.76
     വഹ
    0.76
    노
    0.76
    ẞ
    0.75
    POSITIVE LOGITS
     begin
    3.66
     begins
    3.57
     begun
    3.55
     start
    3.51
     starts
    3.50
     beginning
    3.49
     dimulai
    3.43
     시작
    3.41
     started
    3.41
     commence
    3.33
    Activations Density 1.336%

    No Known Activations