© 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. 11058
    Prev
    Next
    INDEX
    Explanations

    temporal sequence after events

    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
    There
    -2.44
    When
    -2.28
    People
    -2.06
    If
    -2.05
     When
    -1.80
    You
    -1.77
    when
    -1.77
    Because
    -1.75
    Very
    -1.73
     ketika
    -1.69
    POSITIVE LOGITS
     relativamente
    1.66
    などと
    1.63
    recently
    1.63
     finalement
    1.63
     genellikle
    1.58
    honestly
    1.56
     tidligere
    1.54
     zprá
    1.54
     restes
    1.53
     pasamos
    1.51
    Activations Density 0.033%

    No Known Activations