© 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. 10137
    Prev
    Next
    INDEX
    Explanations

    colossal formations and waterfalls

    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
    🚣
    1.05
     kites
    1.00
    🛶
    1.00
     hilly
    0.99
    🏞
    0.98
    🚴
    0.96
    ⛵
    0.96
     gunung
    0.95
    🏊
    0.95
    ⛰
    0.95
    POSITIVE LOGITS
    Dropdown
    1.02
    Drawer
    1.01
     ইলেক্ট্রো
    1.00
     Stal
    1.00
     stigmat
    1.00
     chas
    0.99
     তড়িৎ
    0.99
     बायो
    0.96
     dissolution
    0.96
     hood
    0.96
    Activations Density 0.178%

    No Known Activations