© 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. 97994
    Prev
    Next
    INDEX
    Explanations

    unlimited access

    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
     Walk
    -0.74
    不解
    -0.72
     escorted
    -0.71
    왑
    -0.70
     Pelham
    -0.70
    Barrett
    -0.70
     Barrett
    -0.69
     karşı
    -0.69
    Walk
    -0.68
     operación
    -0.68
    POSITIVE LOGITS
    ܥ
    0.82
    adecimal
    0.79
    цький
    0.69
    endet
    0.68
    tsky
    0.68
     mahu
    0.67
    ګ
    0.66
    ۂ
    0.66
     milk
    0.65
     Validator
    0.65
    Activations Density 0.049%

    No Known Activations