© 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. 931
    Prev
    Next
    INDEX
    Explanations

    game over or running state

    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
     ネイビー
    1.63
     西
    1.54
    hetiti
    1.48
     对象
    1.43
     コットン
    1.41
     青
    1.40
     时尚
    1.39
     删除
    1.38
     世界
    1.38
     北
    1.37
    POSITIVE LOGITS
    so
    0.74
     though
    0.72
    though
    0.71
     daher
    0.71
     so
    0.63
    sof
    0.62
     mutta
    0.60
     fun
    0.60
     spann
    0.60
     derfor
    0.58
    Activations Density 0.019%

    No Known Activations