© 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. 58054
    Prev
    Next
    INDEX
    Explanations

    drop down menu

    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
    bage
    -0.77
     Dumbledore
    -0.76
    ukt
    -0.75
     Dies
    -0.75
     moss
    -0.74
     Shelly
    -0.73
     Wimbledon
    -0.72
    existsSync
    -0.72
    ajte
    -0.72
    readFileSync
    -0.72
    POSITIVE LOGITS
     drop
    5.03
     dropdown
    4.41
    drop
    3.78
    dropdown
    3.77
     Drop
    3.75
    Drop
    3.53
    Dropdown
    3.30
    DropDown
    3.30
     Dropdown
    3.20
    下拉
    3.17
    Activations Density 0.193%

    No Known Activations