© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25916
    Prev
    Next
    INDEX
    Explanations

    Tucson

    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
    รอ
    -0.79
    еты
    -0.76
     innebär
    -0.75
     Barth
    -0.75
    Agra
    -0.74
    ATS
    -0.74
     Hail
    -0.74
     đỏ
    -0.73
    שות
    -0.73
    laceae
    -0.73
    POSITIVE LOGITS
     Tucson
    1.84
    Tucson
    1.48
     tucson
    0.98
    envs
    0.85
    UA
    0.83
     UA
    0.81
     Sah
    0.80
     Coch
    0.78
    帕
    0.76
     Kino
    0.75
    Activations Density 0.012%

    No Known Activations