© 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. 17899
    Prev
    Next
    INDEX
    Explanations

    RSS 2.0 feed and obtain

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

    you could

    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
    Emit
    0.43
    %(
    0.42
    TRANSFER
    0.38
    Armed
    0.38
    PAssignment
    0.38
    PSS
    0.38
    DWORD
    0.38
    撣
    0.38
    プラ
    0.37
    Kumar
    0.37
    POSITIVE LOGITS
     sérieux
    0.43
    abı
    0.43
    可以通过
    0.41
    的一
    0.39
    了一
    0.39
     pb
    0.39
     frères
    0.38
     পত্রিকায়
    0.38
     प्रसिद्ध
    0.38
     megt
    0.38
    Activations Density 0.002%

    No Known Activations