© 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. 1230
    Prev
    Next
    INDEX
    Explanations

    number of

    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
     intrepid
    1.34
     A
    1.26
     Americas
    1.25
     بتت
    1.25
     Approximately
    1.24
    At
    1.19
     At
    1.18
    ついて
    1.16
    Car
    1.15
    শ্বর
    1.15
    POSITIVE LOGITS
    encji
    1.62
    agę
    1.61
    анали
    1.58
     ਦਾ
    1.57
    硏
    1.51
     مسائل
    1.50
    timeslots
    1.47
    ုန်
    1.46
    rinsim
    1.46
    ញ្
    1.45
    Activations Density 0.474%

    No Known Activations