© 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. 90160
    Prev
    Next
    INDEX
    Explanations

    popularity

    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
    rija
    -0.91
    ifiable
    -0.91
    aried
    -0.88
     {?}
    -0.85
    ߣ
    -0.84
    lepiej
    -0.84
    fillment
    -0.81
    ↔
    -0.81
    ícias
    -0.80
    ogg
    -0.80
    POSITIVE LOGITS
     popular
    6.78
     popularity
    5.81
     популяр
    5.38
    popular
    5.34
    Popular
    5.22
     Popular
    4.81
     POPULAR
    4.41
     populares
    4.19
    popularity
    4.03
     Popularity
    4.00
    Activations Density 0.183%

    No Known Activations