© 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. 7487
    Prev
    Next
    INDEX
    Explanations

    Catalan + English topics

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

    Pg. a Catalunya

    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
     ሃ
    0.49
     uhr
    0.47
     زائدا
    0.45
     встре
    0.43
     ንጥረ
    0.43
     heck
    0.43
     लहान
    0.43
     remedied
    0.43
    滪
    0.43
    掷
    0.43
    POSITIVE LOGITS
     treball
    1.35
     aquest
    1.30
     més
    1.29
     també
    1.27
     aquesta
    1.27
     després
    1.26
     perquè
    1.23
     està
    1.23
     dels
    1.12
     encara
    1.11
    Activations Density 0.016%

    No Known Activations