© 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. 124
    Prev
    Next
    INDEX
    Explanations

    symbols and separators

    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
     to
    -1.95
     anunciado
    -1.84
     the
    -1.80
     eenvoudig
    -1.76
     with
    -1.75
     Then
    -1.72
     explicado
    -1.70
    珦
    -1.68
     in
    -1.68
    与其
    -1.60
    POSITIVE LOGITS
    8
    1.83
    4
    1.80
    6
    1.61
    所有的
    1.61
    This
    1.58
    9
    1.56
    Our
    1.53
    2
    1.51
    7
    1.50
    They
    1.49
    Activations Density 0.003%

    No Known Activations