© 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. 81432
    Prev
    Next
    INDEX
    Explanations

    and followed by continuation

    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
    archiwizowane
    -1.76
    gleichen
    -1.74
     ofte
    -1.73
     parfois
    -1.71
     souvent
    -1.70
     dáms
    -1.69
     páns
    -1.67
    mainly
    -1.64
    reisen
    -1.61
    搋
    -1.56
    POSITIVE LOGITS
     when
    4.00
     after
    3.45
     before
    3.36
     it
    2.98
     while
    2.83
     then
    2.78
     since
    2.77
     during
    2.75
     although
    2.73
     despite
    2.69
    Activations Density 0.094%

    No Known Activations