© 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. 13-GEMMASCOPE-2-RES-65K
    7. 101
    Prev
    Next
    INDEX
    Explanations

    unique names or words

    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_65k_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
     re
    0.95
     led
    0.94
    ,
    0.94
     actually
    0.90
     ​​
    0.89
     takeaway
    0.88
     having
    0.88
     putting
    0.87
     served
    0.87
     actual
    0.87
    POSITIVE LOGITS
    婼
    1.43
     средств
    1.43
    ภาษา
    1.42
    <unused1285>
    1.42
     sebagainya
    1.41
    थोरो
    1.40
     penyakit
    1.40
    फाली
    1.38
    方法
    1.38
    环境
    1.36
    Activations Density 0.022%

    No Known Activations