© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    common determiner for nouns

    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
     ✨
    1.17
     coordinated
    1.16
    coordinated
    1.10
    无需
    1.09
     customized
    1.07
     ✅
    1.07
     প্রতিটি
    1.06
     специализирован
    1.06
     不需要
    1.05
    🖤
    1.03
    POSITIVE LOGITS
    議論
    1.27
     얘기를
    1.19
     situation
    1.18
    這位
    1.12
    这位
    1.12
     anecdote
    1.10
     comentario
    1.08
     tragedy
    1.08
     argument
    1.08
     topic
    1.07
    Activations Density 0.569%

    No Known Activations