© 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. 109172
    Prev
    Next
    INDEX
    Explanations

    probability questions involving sets

    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
    փ
    -0.87
     KH
    -0.85
     xy
    -0.84
     ZA
    -0.81
     BA
    -0.79
    KH
    -0.77
     XC
    -0.76
    DA
    -0.76
     margen
    -0.76
    ;\
    -0.75
    POSITIVE LOGITS
     S
    0.87
     C
    0.84
     A
    0.82
     screenshot
    0.77
    SharedModule
    0.73
    Kariera
    0.71
    hopped
    0.71
    Republicans
    0.70
     infrequent
    0.69
     M
    0.69
    Activations Density 0.183%

    No Known Activations