© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14307
    Prev
    Next
    INDEX
    Explanations

    economics concepts

    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
    bs
    2.51
    𝐫
    2.37
    𝐮
    2.24
    𝐥
    2.23
    𝐭
    2.19
    𝐛
    2.13
    𝐠
    2.10
    boi
    2.09
    bo
    2.09
    𝐬
    2.09
    POSITIVE LOGITS
    𝑖
    3.31
    お知らせ
    3.19
    ią
    3.14
    िया
    3.10
    ాము
    2.97
    iędzy
    2.95
    ię
    2.89
    تف
    2.88
    蜢
    2.87
     [['
    2.83
    Activations Density 0.029%

    No Known Activations