© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15976
    Prev
    Next
    INDEX
    Explanations

    certified product, distributed file, frequency modulation

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

    terms following "Distributed", "Automotive", "Artificial", "Rapid", "Large", "Maximum", "Minimum"

    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_31_width_16k_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
     ಹೆಸ
    0.48
     België
    0.47
     मई
    0.44
     Mugh
    0.42
     söz
    0.42
     أب
    0.42
    𝓊
    0.42
    珺
    0.42
     न्यूज
    0.41
    ंजलि
    0.41
    POSITIVE LOGITS
     acronym
    0.48
    ahydro
    0.46
    otransfer
    0.44
     termed
    0.43
     hydrodynamic
    0.43
     kilogram
    0.42
     polymerase
    0.41
     Automated
    0.41
     Electrochemical
    0.41
     wavenumber
    0.41
    Activations Density 0.311%

    No Known Activations