© 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. 25788
    Prev
    Next
    INDEX
    Explanations

    object properties

    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
    衛隊
    -0.89
    uksessa
    -0.78
    kanan
    -0.76
    anoia
    -0.76
    版权
    -0.73
    ур
    -0.72
    sApp
    -0.72
    ناول
    -0.71
    теше
    -0.71
    oznam
    -0.71
    POSITIVE LOGITS
    attributes
    1.15
     attributes
    1.15
    fields
    1.09
     fields
    1.05
    acf
    1.01
     properties
    0.93
    snippet
    0.84
    Attributes
    0.82
    JoinColumn
    0.81
     Fields
    0.81
    Activations Density 0.018%

    No Known Activations