© 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. 59884
    Prev
    Next
    INDEX
    Explanations

    related to location and targets

    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
     when
    -2.03
     in
    -1.92
     if
    -1.88
     for
    -1.86
     because
    -1.80
     after
    -1.67
    to
    -1.65
     at
    -1.64
    🫶
    -1.63
     before
    -1.59
    POSITIVE LOGITS
     tijdens
    1.78
    several
    1.76
     portatil
    1.73
     Atención
    1.68
     επίσης
    1.68
     merkwür
    1.66
     utilisent
    1.65
     besoin
    1.63
    
    1.61
     forbidding
    1.60
    Activations Density 0.002%

    No Known Activations