© 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. 23509
    Prev
    Next
    INDEX
    Explanations

    Field of Invention or Registration Process

    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
     lamented
    -0.88
     منذ
    -0.82
    UnifiedTopology
    -0.80
    凜
    -0.78
    کل
    -0.77
     Erwachsenen
    -0.77
    Nå
    -0.77
    Рецепт
    -0.76
    Fro
    -0.75
     desvi
    -0.74
    POSITIVE LOGITS
     Prosperity
    0.77
    CONTACTS
    0.75
     honey
    0.75
    Claus
    0.75
     CAM
    0.74
    setNome
    0.73
     parad
    0.71
    Uninitialized
    0.71
    随即
    0.70
     вдоль
    0.70
    Activations Density 0.012%

    No Known Activations