© 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. 118197
    Prev
    Next
    INDEX
    Explanations

    code comments and licensing

    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
    ֵי
    -0.76
    istiche
    -0.66
     đá
    -0.65
    Hc
    -0.65
    刽
    -0.64
    awatan
    -0.64
     sám
    -0.64
    დი
    -0.64
     keV
    -0.64
    Afrique
    -0.63
    POSITIVE LOGITS
    แต
    0.63
     fällt
    0.63
    aller
    0.63
     Phosp
    0.62
     phosphat
    0.62
    类别
    0.62
     assertion
    0.60
    ないように
    0.60
     securities
    0.59
    mith
    0.59
    Activations Density 0.082%

    No Known Activations