© 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. 73476
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with $

    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
    Welt
    -0.82
    达
    -0.75
    ʌ
    -0.73
    expert
    -0.72
     when
    -0.71
     despite
    -0.70
     Welt
    -0.68
     pengunjung
    -0.67
     investasi
    -0.67
    واف
    -0.67
    POSITIVE LOGITS
    DRAG
    0.86
     MSE
    0.85
     requisite
    0.83
    Referencer
    0.82
    TryParse
    0.82
     ridiculously
    0.80
     Viss
    0.80
     mimicking
    0.79
    StartsWith
    0.79
    􀀀
    0.79
    Activations Density 0.128%

    No Known Activations