Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2867
    Prev
    Next
    INDEX
    Explanations

    loops and indices

    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
    Ⅸ
    1.30
     собак
    1.23
    ඪ
    1.23
     ষ্ট
    1.22
    龰
    1.22
    Saint
    1.19
     животных
    1.18
     ";//
    1.18
    觡
    1.18
    Jack
    1.16
    POSITIVE LOGITS
     eminently
    0.98
     regardless
    0.88
     pointy
    0.87
     unless
    0.86
     unreasonably
    0.85
    ్‌
    0.83
     whether
    0.82
     arbitrary
    0.81
     squarely
    0.80
     either
    0.79
    Activations Density 0.001%

    No Known Activations