© 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. 7-GEMMASCOPE-2-RES-16K
    4. 14224
    Prev
    Next
    INDEX
    Explanations

    facebook login, learn, business, marketplace

    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_7_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
     forgiveness
    1.02
     people
    1.01
    죄
    1.00
    ServerError
    0.96
     amnesty
    0.93
    people
    0.92
     людей
    0.91
    People
    0.90
    зи
    0.89
     truce
    0.86
    POSITIVE LOGITS
     ইন্ড
    1.11
     phổ
    1.11
     অত্যা
    1.09
     alkalies
    1.08
     cường
    1.08
    尖
    1.08
    フォーマンス
    1.06
    kových
    1.05
    含量
    0.98
    crystalline
    0.97
    Activations Density 0.003%

    No Known Activations