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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 520
    Prev
    Next
    INDEX
    Explanations

    asking for aims

    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
     again
    0.67
     new
    0.65
    http
    0.63
     http
    0.62
    ^
    0.61
     unduly
    0.60
     www
    0.60
    ­
    0.60
    www
    0.60
     revised
    0.59
    POSITIVE LOGITS
     بالإضافة
    1.09
     আশেপাশে
    1.08
     Além
    1.05
    受欢迎
    1.04
     Además
    1.03
     प्रॉपर्टी
    1.02
     destacar
    1.02
     angegeben
    1.02
    भवती
    1.01
     aproximadamente
    1.00
    Activations Density 1.085%

    No Known Activations