© 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. 31417
    Prev
    Next
    INDEX
    Explanations

    posting and uploading

    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
     cincin
    -0.90
    nosa
    -0.89
     argento
    -0.87
     mariana
    -0.87
     собра
    -0.87
     fatte
    -0.85
     avesse
    -0.84
     cavo
    -0.82
    脚注
    -0.82
     pittore
    -0.82
    POSITIVE LOGITS
     upload
    1.18
     uploading
    1.09
     postings
    1.00
    upload
    0.98
     posting
    0.96
     uploads
    0.94
    UPLOAD
    0.89
     uploaded
    0.89
    Upload
    0.86
     Upload
    0.83
    Activations Density 0.024%

    No Known Activations