© 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. 33116
    Prev
    Next
    INDEX
    Explanations

    product details and 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
     الآخر
    -0.85
    iges
    -0.81
     другие
    -0.81
    找
    -0.80
     conhecido
    -0.80
     outras
    -0.80
    勿論
    -0.80
     スキ
    -0.79
     tuyên
    -0.79
     gleiche
    -0.79
    POSITIVE LOGITS
     JpaRepository
    0.98
     kä
    0.94
    KHz
    0.91
    #}
    0.90
     føl
    0.90
     virtudes
    0.90
     curly
    0.89
     americanos
    0.88
     postage
    0.85
     sombras
    0.85
    Activations Density 0.028%

    No Known Activations