© 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. 22-GEMMASCOPE-RES-131K
    7. 84537
    Prev
    Next
    INDEX
    Explanations

    true, success, ok, zero

    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_22/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
     prada
    -0.86
    澎
    -0.83
    sdp
    -0.82
     standen
    -0.82
     resultMap
    -0.81
     memutus
    -0.80
    viewWillAppear
    -0.80
    rías
    -0.80
    ethene
    -0.79
    🩱
    -0.79
    POSITIVE LOGITS
    這款
    1.00
    聽到
    0.96
    餐廳
    0.96
    뭘
    0.94
    我对
    0.92
    Сту
    0.92
    來自
    0.91
    خرید
    0.91
    每個
    0.89
    Κ
    0.89
    Activations Density 0.005%

    No Known Activations