© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14666
    Prev
    Next
    INDEX
    Explanations

    lists containing symbols, citations, or examples

    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
    蔔
    2.06
     thủy
    1.74
     ㅅ
    1.72
     doanh
    1.67
     犬
    1.65
    htra
    1.65
    사이
    1.62
    로드
    1.60
     pipe
    1.59
    킥
    1.58
    POSITIVE LOGITS
    <h4>
    1.89
    <h1>
    1.67
    ো
    1.60
    <h3>
    1.53
    Еще
    1.49
    eastern
    1.48
     კიდ
    1.41
    additional
    1.40
    Wait
    1.39
    િ
    1.38
    Activations Density 0.005%

    No Known Activations