© 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. 117369
    Prev
    Next
    INDEX
    Explanations

    upload/distribute/submit

    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
    fscanf
    -0.79
    glGet
    -0.76
     brass
    -0.70
     redirect
    -0.70
    brück
    -0.69
    ustu
    -0.68
     vinyl
    -0.68
     diving
    -0.68
    lâ
    -0.68
     Pran
    -0.67
    POSITIVE LOGITS
     upload
    5.53
     uploading
    4.72
    upload
    4.50
     uploaded
    4.38
    Upload
    4.25
     Upload
    4.22
    上传
    4.06
     uploads
    3.95
    UPLOAD
    3.52
     上传
    3.30
    Activations Density 0.170%

    No Known Activations