© 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. 22-GEMMASCOPE-2-RES-16K
    7. 575
    Prev
    Next
    INDEX
    Explanations

    technical terms and non-English words

    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_22_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
    了
    1.87
    nya
    1.79
    ので
    1.66
    ्स
    1.49
    น้ำ
    1.47
    นิ
    1.44
    د
    1.42
    นี
    1.41
    น
    1.38
    น่า
    1.31
    POSITIVE LOGITS
    ện
    1.50
    ñ
    1.49
    pper
    1.48
    ệu
    1.37
    pped
    1.36
    ョ
    1.36
    깐
    1.33
    ệt
    1.33
    yah
    1.33
    ya
    1.33
    Activations Density 0.423%

    No Known Activations