© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17259
    Prev
    Next
    INDEX
    Explanations

    collocations with verbs and prepositions

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

    explaining or comparing information

    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
     हुये
    0.41
     یافته
    0.40
    িয়৷
    0.39
     তাঁকে
    0.39
     তৈরী
    0.37
     দিয়েছে
    0.36
    :
    0.36
     yapmış
    0.35
    されている
    0.35
     వు
    0.35
    POSITIVE LOGITS
     ALSO
    0.54
     AGAIN
    0.45
     specifically
    0.41
     برضو
    0.40
     ㄹ
    0.39
    Specifically
    0.39
     ასევე
    0.39
     একইভাবে
    0.38
    ⑮
    0.38
     wiederum
    0.38
    Activations Density 0.088%

    No Known Activations