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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6117
    Prev
    Next
    INDEX
    Explanations

    comparing data and research

    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_13_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
    ی
    1.45
    ň
    1.30
    שו
    1.18
    ી
    1.15
    ্
    1.14
    yas
    1.14
     Freeway
    1.11
    মাপ
    1.10
    kana
    1.10
     punto
    1.10
    POSITIVE LOGITS
     快
    1.46
     赤
    1.31
     沙
    1.30
    뭣
    1.29
     不能
    1.26
     час
    1.26
    릭
    1.25
     而且
    1.25
     เพื่อน
    1.25
     大家
    1.24
    Activations Density 0.000%

    No Known Activations