© 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. 81369
    Prev
    Next
    INDEX
    Explanations

    data mining and knowledge discovery

    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
     decoding
    -0.71
    esomeness
    -0.70
     calculating
    -0.68
     Kebijakan
    -0.68
     програм
    -0.68
     Calculating
    -0.67
     εισ
    -0.67
    fig
    -0.66
     え
    -0.66
     sempre
    -0.66
    POSITIVE LOGITS
    grub
    0.92
     KD
    0.91
    Knowledge
    0.90
    Discovery
    0.85
     discovery
    0.85
     recevez
    0.84
    KD
    0.80
     DM
    0.79
    zoic
    0.77
    Mining
    0.77
    Activations Density 0.022%

    No Known Activations