© 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. 75898
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and sequences

    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
     respectively
    -0.77
     mentioned
    -0.75
     Ukra
    -0.75
     Wiz
    -0.74
     φο
    -0.73
    一样
    -0.73
    straße
    -0.73
     mentions
    -0.71
     أخرى
    -0.71
     mention
    -0.71
    POSITIVE LOGITS
     Agrega
    0.88
    ğraf
    0.82
    toolkit
    0.81
    );"
    0.81
    fficking
    0.81
     פרק
    0.80
     ല
    0.78
    cipation
    0.78
    leps
    0.76
     hızlı
    0.76
    Activations Density 0.029%

    No Known Activations