© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2104
    Prev
    Next
    INDEX
    Explanations

    edit

    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
    ͷ
    -0.74
    uib
    -0.73
     ukraine
    -0.72
    amp
    -0.70
     myco
    -0.67
    🪨
    -0.66
    igma
    -0.66
    agan
    -0.65
    плот
    -0.65
    wali
    -0.64
    POSITIVE LOGITS
     edit
    1.69
    Edit
    1.57
     Edit
    1.45
    edit
    1.42
     editors
    1.38
     edits
    1.38
     EDIT
    1.31
    EDIT
    1.26
     editing
    1.22
     Editors
    1.19
    Activations Density 0.005%

    No Known Activations