© 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. 53936
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     chug
    -0.82
    金沢
    -0.81
     سواء
    -0.80
     MSM
    -0.79
     administração
    -0.76
     Där
    -0.75
    これは
    -0.75
    ヘ
    -0.74
    ５
    -0.74
    ฉ
    -0.74
    POSITIVE LOGITS
     and
    0.92
     resultMap
    0.81
    cauc
    0.81
    DAV
    0.80
    甑
    0.79
     kato
    0.78
     топлива
    0.78
    ‾
    0.77
    тє
    0.76
     photos
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.