© 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. 1053
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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
     local
    0.86
     ….
    0.83
     locally
    0.83
    </i>
    0.82
     [
    0.81
     full
    0.79
     other
    0.77
     non
    0.76
     -
    0.76
    ""
    0.75
    POSITIVE LOGITS
     بالټ
    1.57
    ſ
    1.57
    ၣ်
    1.56
    ⁤
    1.55
     المصفوفه
    1.53
    GEBURTS
    1.53
    ⁢
    1.48
    
    1.47
     فونبیټ
    1.46
    ‌اند
    1.45
    Activations Density 13.698%

    No Known Activations