© 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. 97902
    Prev
    Next
    INDEX
    Explanations

    boilerplate and copyright notices

    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
     have
    -0.77
    ນ
    -0.73
     Dick
    -0.71
    Dick
    -0.71
     nematode
    -0.69
     emosi
    -0.69
     Gorge
    -0.68
    VC
    -0.68
    رفع
    -0.68
    
    -0.66
    POSITIVE LOGITS
     번
    0.69
     unor
    0.68
    Alam
    0.68
     outboard
    0.68
    Heel
    0.68
    hemian
    0.68
    ERGY
    0.66
    edom
    0.66
    erval
    0.66
     Suns
    0.65
    Activations Density 0.055%

    No Known Activations