© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77701
    Prev
    Next
    INDEX
    Explanations

    software layers and components

    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
    مصادر
    -0.83
    webhook
    -0.81
    certs
    -0.79
    BaseController
    -0.79
    جمعیت
    -0.79
     ビル
    -0.77
    Normally
    -0.77
    Usually
    -0.77
    нали
    -0.77
    Nr
    -0.76
    POSITIVE LOGITS
    层
    2.14
     layer
    2.11
    層
    1.81
    layer
    1.80
    层的
    1.75
     LAYER
    1.65
    Layer
    1.56
     Layer
    1.52
     layers
    1.29
    LAYER
    1.24
    Activations Density 0.075%

    No Known Activations