© 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. 10-GEMMASCOPE-RES-131K
    7. 75577
    Prev
    Next
    INDEX
    Explanations

    states become available

    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
    ！(
    -1.28
     all
    -1.26
     still
    -1.23
     an
    -1.20
     a
    -1.19
        
    -1.15
     instituto
    -1.14
    if
    -1.13
     another
    -1.11
     just
    -1.09
    POSITIVE LOGITS
     poszczegól
    1.87
     jeweiligen
    1.61
     einzelnen
    1.46
     jednotliv
    1.46
     entsprechenden
    1.45
     tatsäch
    1.34
     olika
    1.32
     różne
    1.30
     geschlagen
    1.24
     разные
    1.23
    Activations Density 0.049%

    No Known Activations