© 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. 82261
    Prev
    Next
    INDEX
    Explanations

    geometric surfaces and patches

    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
     problemów
    -0.73
    yb
    -0.71
     gate
    -0.69
     dating
    -0.69
     Sua
    -0.69
     Pois
    -0.68
    lawyer
    -0.68
     najbolj
    -0.68
    madre
    -0.66
    ciles
    -0.66
    POSITIVE LOGITS
     NUR
    1.05
     CAG
    1.02
     patches
    1.02
    patch
    0.98
    Surface
    0.96
     surface
    0.96
    CAG
    0.94
    patches
    0.94
     Nur
    0.93
     patch
    0.93
    Activations Density 0.026%

    No Known Activations