© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 144
    Prev
    Next
    INDEX
    Explanations

    Markdown list and heading markers

    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
    ↵↵
    1.57
    ↵
    1.55
     II
    1.48
     β
    1.46
     halt
    1.43
     ’
    1.41
     re
    1.39
     ​​
    1.39
     /
    1.38
     III
    1.37
    POSITIVE LOGITS
    <blockquote>
    3.12
    Dalam
    2.85
    Selain
    2.82
    There
    2.80
    Это
    2.72
    Dengan
    2.72
    Although
    2.71
    Tidak
    2.70
    În
    2.68
    <h5>
    2.68
    Activations Density 1.783%

    No Known Activations