© 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. 117930
    Prev
    Next
    INDEX
    Explanations

    post-processing or classification result

    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
     Lucca
    -0.81
     modernization
    -0.77
    訓練
    -0.76
     farmhouse
    -0.75
    調査
    -0.74
     strto
    -0.74
     training
    -0.71
    训练
    -0.71
     Weapons
    -0.71
    濱
    -0.71
    POSITIVE LOGITS
    nms
    1.51
    Post
    1.09
     post
    0.96
    post
    0.95
     Post
    0.91
     logiciels
    0.86
    accepted
    0.84
    cheon
    0.82
    threshold
    0.81
     compartilhar
    0.80
    Activations Density 0.007%

    No Known Activations