© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12489
    Prev
    Next
    INDEX
    Explanations

    category theory and its structures

    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_10/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
     during
    -1.73
     after
    -1.42
     intricacies
    -1.36
     пом
    -1.30
    petito
    -1.30
     Drittan
    -1.25
     will
    -1.24
     from
    -1.23
    er
    -1.23
     víc
    -1.21
    POSITIVE LOGITS
    </b>
    1.82
    вані
    1.73
    єра
    1.55
    黑的
    1.50
    зите
    1.49
    </h4>
    1.45
    marked
    1.45
     diverses
    1.42
     overly
    1.41
     extremely
    1.40
    Activations Density 0.039%

    No Known Activations