© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77315
    Prev
    Next
    INDEX
    Explanations

    United Nations organizations and documents

    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
    Nice
    -0.87
    anmoins
    -0.82
     posterity
    -0.81
    brida
    -0.80
    rieden
    -0.75
    宥
    -0.73
    Docket
    -0.73
    weetie
    -0.73
    존
    -0.73
     Nice
    -0.72
    POSITIVE LOGITS
     UNDP
    0.80
    Uart
    0.79
    soy
    0.79
    ことはない
    0.77
     oso
    0.77
    Segmentation
    0.75
    ⼿
    0.75
     mysteries
    0.73
     realized
    0.72
     dets
    0.71
    Activations Density 0.025%

    No Known Activations