© 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. 58534
    Prev
    Next
    INDEX
    Explanations

    arguments and parameters

    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
    inique
    -0.91
    acji
    -0.84
     działalności
    -0.81
    backs
    -0.80
    pă
    -0.77
    增强
    -0.77
    击
    -0.76
     februarie
    -0.75
     mérite
    -0.75
     indexPath
    -0.75
    POSITIVE LOGITS
     scroll
    1.18
     Scroll
    0.98
    resizable
    0.97
     scrolling
    0.94
     status
    0.90
     men
    0.90
    scrolling
    0.86
    scroll
    0.81
     Status
    0.81
     toolbar
    0.80
    Activations Density 0.011%

    No Known Activations