© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3112
    Prev
    Next
    INDEX
    Explanations

    organizations and acronyms

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

    specific acronyms and organizations

    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
     După
    0.41
    Dr
    0.40
    </em>
    0.39
     Include
    0.38
    Its
    0.38
    </strong>
    0.38
    тальян
    0.36
     Its
    0.36
     भारतातील
    0.36
    <unused61>
    0.36
    POSITIVE LOGITS
     MNIST
    0.63
     Obamacare
    0.57
     LIGO
    0.56
     IELTS
    0.54
     Гос
    0.53
     MSCI
    0.52
     OSHA
    0.52
     QuickBooks
    0.52
     IPCC
    0.50
     FEMA
    0.50
    Activations Density 0.454%

    No Known Activations