© 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. 23873
    Prev
    Next
    INDEX
    Explanations

    neural followed by technical terms

    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
    는
    -0.91
     يعني
    -0.88
    是一种
    -0.85
    は
    -0.84
    を
    -0.81
    нимание
    -0.79
    よりも
    -0.79
    ԁ
    -0.78
     ตัว
    -0.76
     herói
    -0.76
    POSITIVE LOGITS
    gia
    1.09
     network
    1.06
     networks
    1.02
     Network
    0.93
    gias
    0.88
    network
    0.88
    rencies
    0.85
    Network
    0.84
    stine
    0.83
     firing
    0.83
    Activations Density 0.027%

    No Known Activations