© 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. 83227
    Prev
    Next
    INDEX
    Explanations

    `Athlone`, `Dayton artist`, `Granard`, `Q:`, `<?xml`

    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
    Strike
    -0.82
    retudo
    -0.80
     Cork
    -0.80
    tráfico
    -0.79
    祎
    -0.78
     Strike
    -0.78
     relacionados
    -0.73
     References
    -0.73
    焓
    -0.73
     animal
    -0.71
    POSITIVE LOGITS
     goals
    0.92
     composit
    0.84
     parallelogram
    0.78
     yeşil
    0.75
     majors
    0.75
    enrollment
    0.73
     forage
    0.73
    Goals
    0.72
     tricolor
    0.72
     vodou
    0.72
    Activations Density 0.027%

    No Known Activations