© 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. 25568
    Prev
    Next
    INDEX
    Explanations

    hosting SNL

    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
    teca
    -0.82
     at
    -0.80
     journée
    -0.79
     anonymity
    -0.77
    unhofer
    -0.77
     examining
    -0.77
     produces
    -0.77
     Vim
    -0.75
    aggia
    -0.72
     convenio
    -0.72
    POSITIVE LOGITS
     host
    1.52
     hosting
    1.45
    hosted
    1.38
    host
    1.23
    Hosted
    1.22
     hosted
    1.21
    hosting
    1.21
     Hosting
    1.20
    HOST
    1.19
     SNL
    1.19
    Activations Density 0.013%

    No Known Activations