© 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. 17-GEMMASCOPE-2-RES-16K
    7. 543
    Prev
    Next
    INDEX
    Explanations

    code output and execution

    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
     ,
    1.00
     slogan
    0.91
     repealed
    0.90
     ’
    0.89
    athons
    0.88
    pronounced
    0.85
    -,
    0.85
     INNOV
    0.82
    crets
    0.80
    ⅼ
    0.80
    POSITIVE LOGITS
    if
    1.96
     nếu
    1.89
     if
    1.81
     jika
    1.80
    หาก
    1.79
    return
    1.73
    ถ้า
    1.69
     dacă
    1.68
     kalau
    1.63
    если
    1.62
    Activations Density 0.048%

    No Known Activations