© 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. 90598
    Prev
    Next
    INDEX
    Explanations

    examining possibilities and situations

    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
    ñado
    -1.04
    ऽ
    -0.95
     googling
    -0.94
     chú
    -0.92
    ít
    -0.92
    某种
    -0.91
    enden
    -0.91
    的一部分
    -0.89
    isse
    -0.89
    crapers
    -0.88
    POSITIVE LOGITS
     whether
    1.88
     available
    1.80
     possible
    1.70
     how
    1.65
     options
    1.64
     possibilities
    1.63
     trends
    1.55
     why
    1.55
     potential
    1.54
     situation
    1.53
    Activations Density 0.187%

    No Known Activations