© 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. 76586
    Prev
    Next
    INDEX
    Explanations

    social media

    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
    prits
    -0.84
     Gun
    -0.79
    Tint
    -0.77
    홍
    -0.77
     facture
    -0.76
    韧
    -0.74
    mutations
    -0.74
     cheio
    -0.72
    guntas
    -0.71
     fulness
    -0.71
    POSITIVE LOGITS
     media
    2.63
    media
    1.72
    Media
    1.56
     Media
    1.52
    媒体
    1.51
    MEDIA
    1.37
     MEDIA
    1.30
     platforms
    1.13
     networking
    1.13
     medier
    1.13
    Activations Density 0.011%

    No Known Activations