© 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. 78196
    Prev
    Next
    INDEX
    Explanations

    median and average statistics

    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
    PubMed
    -0.83
    是的
    -0.83
    监听
    -0.81
    podes
    -0.77
     nemoc
    -0.74
    deutung
    -0.73
     bicchiere
    -0.73
    Utilization
    -0.73
     gebildet
    -0.73
    fsm
    -0.72
    POSITIVE LOGITS
    ƃ
    0.72
     sold
    0.71
     priced
    0.70
     modernas
    0.69
     gamer
    0.69
     Stevenson
    0.68
    Concerns
    0.68
    male
    0.67
    浏览
    0.67
     superhero
    0.66
    Activations Density 0.039%

    No Known Activations