© 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. 107395
    Prev
    Next
    INDEX
    Explanations

    numbers and scores

    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
     five
    -1.62
    five
    -1.59
     thousands
    -1.59
     eight
    -1.50
     seven
    -1.45
     ten
    -1.44
     six
    -1.44
    Five
    -1.41
     Five
    -1.41
    eight
    -1.41
    POSITIVE LOGITS
     sixty
    2.27
     seventy
    2.27
     Sixty
    2.25
     Seventy
    2.14
     fifty
    2.13
     Fifty
    2.03
    Fifty
    2.02
    Sixty
    2.00
     eighty
    1.94
     Forty
    1.81
    Activations Density 0.285%

    No Known Activations