© 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. 93209
    Prev
    Next
    INDEX
    Explanations

    social networking and 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
    ⁣
    -0.82
     Thanos
    -0.80
     LGBTQ
    -0.80
     gummies
    -0.79
    ⍳
    -0.78
    ubakar
    -0.77
    デーション
    -0.77
    Adjacent
    -0.77
    ITUTE
    -0.77
     bae
    -0.76
    POSITIVE LOGITS
     networking
    2.02
     social
    1.66
    networking
    1.61
     sites
    1.59
     site
    1.52
     network
    1.49
     networks
    1.48
     Networking
    1.47
     Facebook
    1.44
     Social
    1.44
    Activations Density 0.059%

    No Known Activations