© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1574
    Prev
    Next
    INDEX
    Explanations

    determiners and quantifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    the or your followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     стоковое
    0.33
     бі
    0.33
    ٗ
    0.31
    𝔻
    0.31
    
    0.30
     txtbtn
    0.30
    𝚘
    0.29
    𝗈
    0.29
     ку
    0.29
    并未
    0.29
    POSITIVE LOGITS
     aforementioned
    0.54
     proposed
    0.33
    oretically
    0.33
     overall
    0.33
     مذکور
    0.32
     same
    0.31
     remaining
    0.29
     उक्त
    0.29
     actual
    0.29
     above
    0.28
    Activations Density 3.475%

    No Known Activations