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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3263
    Prev
    Next
    INDEX
    Explanations

    so-called or named

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

    so-called, called, denominado

    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
    </blockquote>
    0.47
    糀
    0.38
     смысла
    0.37
    ोलॉजी
    0.36
     الاشتراك
    0.36
    󰡕
    0.36
    很快
    0.35
    电子商务
    0.35
    鈥
    0.35
    뒀
    0.35
    POSITIVE LOGITS
     cosidd
    0.50
     denominado
    0.41
     sogenannte
    0.39
    所謂
    0.36
     sogen
    0.36
    called
    0.36
     chamado
    0.36
     sogenannten
    0.36
     označ
    0.35
     zog
    0.34
    Activations Density 0.124%

    No Known Activations