© 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. 115565
    Prev
    Next
    INDEX
    Explanations

    code ending punctuation

    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
     erop
    -1.02
     getWidth
    -1.00
     such
    -0.96
     butterknife
    -0.96
     LoginForm
    -0.94
     مانند
    -0.90
    newList
    -0.90
     @"";
    -0.90
     tropicales
    -0.89
     blockSize
    -0.89
    POSITIVE LOGITS
    console
    2.20
     console
    1.94
     setTimeout
    1.54
    setTimeout
    1.52
     let
    1.48
    let
    1.40
    var
    1.36
    document
    1.32
     document
    1.29
    parseInt
    1.19
    Activations Density 0.019%

    No Known Activations