© 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. 1570
    Prev
    Next
    INDEX
    Explanations

    you don't have to

    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
     PLEASE
    1.08
     plz
    1.07
     HAVE
    1.06
     VERY
    1.03
     please
    1.03
    :')
    1.01
     viable
    1.01
    :'
    1.00
    めっちゃ
    0.99
     comply
    0.99
    POSITIVE LOGITS
     нередко
    1.17
     spesso
    1.06
     často
    1.04
     अक्सर
    1.01
     često
    1.01
    often
    1.00
     often
    1.00
    Often
    0.97
    常常
    0.94
    Talking
    0.92
    Activations Density 0.551%

    No Known Activations