© 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. 50365
    Prev
    Next
    INDEX
    Explanations

    spatial predictive

    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
    吏
    -0.80
    Identyfik
    -0.73
    irov
    -0.70
    ització
    -0.70
     Pire
    -0.69
    âh
    -0.69
     foolish
    -0.69
     manila
    -0.68
    دت
    -0.68
     Edelman
    -0.67
    POSITIVE LOGITS
    Fusion
    0.83
     piloto
    0.83
     fusion
    0.81
     Fusion
    0.77
     productos
    0.76
     getCount
    0.75
     représenter
    0.74
     produits
    0.73
     tego
    0.71
     downs
    0.71
    Activations Density 0.022%

    No Known Activations