© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 53915
    Prev
    Next
    INDEX
    Explanations

    product descriptions and names

    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
     Configuración
    -0.94
     Resolución
    -0.94
     conteúdo
    -0.93
    ⱼ
    -0.92
     ページ
    -0.91
     resolução
    -0.91
    ichord
    -0.90
    paksa
    -0.90
     ボタン
    -0.89
    tilles
    -0.89
    POSITIVE LOGITS
     cheap
    1.45
     wholesale
    1.26
     affordable
    1.16
     best
    1.11
     sää
    1.07
     luxury
    1.03
    Best
    1.02
     aluminium
    1.00
     églises
    0.99
    賁
    0.98
    Activations Density 0.074%

    No Known Activations