© 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. 22-GEMMASCOPE-2-RES-16K
    7. 803
    Prev
    Next
    INDEX
    Explanations

    flowers followed by exclamation

    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_22_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
     agak
    1.04
     principally
    1.01
     করলেও
    0.99
     হয়ত
    0.97
    particular
    0.93
     ờ
    0.93
     হয়তো
    0.92
     เงี้ย
    0.91
     chiefly
    0.90
     particular
    0.90
    POSITIVE LOGITS
    !
    5.22
    !!
    5.11
    !!!
    4.94
    !!!!
    4.71
    ！
    4.58
     !
    4.39
    !!!!!
    4.34
    !!!!!!
    4.27
     !!
    4.21
    !”
    4.19
    Activations Density 5.416%

    No Known Activations