© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1492
    Prev
    Next
    INDEX
    Explanations

    consequences and the world

    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
    默
    1.31
    ล
    1.16
    欢
    1.12
    ลก
    1.09
    <0xEF>
    1.07
     Функ
    1.07
    姓
    1.06
    苟
    1.05
     Аб
    1.04
    ต
    1.03
    POSITIVE LOGITS
     etwas
    1.72
     somewhat
    1.52
     perubahan
    1.51
     sweeping
    1.51
     tampilan
    1.49
     ranging
    1.45
     menggunakan
    1.45
     relatively
    1.45
     noting
    1.43
     adjusting
    1.42
    Activations Density 0.480%

    No Known Activations