© 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. 34551
    Prev
    Next
    INDEX
    Explanations

    on the verge

    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
    视为
    -0.92
     ovvero
    -0.86
     olje
    -0.81
     shuffling
    -0.78
    
    -0.77
     validés
    -0.75
     discapacidad
    -0.75
    hile
    -0.75
     حاول
    -0.75
    Batis
    -0.74
    POSITIVE LOGITS
     lookout
    1.93
     receiving
    1.76
     forefront
    1.49
    receiving
    1.48
    Receiving
    1.40
     verge
    1.34
     Receiving
    1.26
     vanguard
    1.25
     cusp
    1.23
     brink
    1.23
    Activations Density 0.023%

    No Known Activations