© 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. 107699
    Prev
    Next
    INDEX
    Explanations

    code comments and license information

    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
     ocul
    -0.75
     possibilities
    -0.70
     mesta
    -0.68
    岡
    -0.68
     Mite
    -0.68
    عبد
    -0.66
     эффективность
    -0.66
    幸いです
    -0.65
     nervosa
    -0.65
     Reit
    -0.65
    POSITIVE LOGITS
     Turks
    1.34
     Provo
    0.98
     Cheshire
    0.94
     TUR
    0.90
     Durham
    0.86
     Turk
    0.84
    enciales
    0.84
    tcl
    0.81
    равни
    0.80
     zainteres
    0.79
    Activations Density 0.009%

    No Known Activations