© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4222
    Prev
    Next
    INDEX
    Explanations

    code/technical terms, dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     know
    -1.01
     crv
    -0.84
     bret
    -0.82
     fch
    -0.81
     trs
    -0.79
     vns
    -0.79
     ddr
    -0.78
    😊
    -0.78
     GRANDE
    -0.78
    mods
    -0.78
    POSITIVE LOGITS
    ਫ਼
    0.84
    คือ
    0.81
     Оте
    0.81
     Excelsior
    0.80
    還是
    0.80
     Autorin
    0.78
     preprint
    0.77
     CTV
    0.77
     (_.
    0.77
     ещё
    0.76
    Activations Density 0.003%

    No Known Activations