© 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. 11984
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    ξω
    -0.79
    で見る
    -0.70
     tàu
    -0.70
    
    -0.70
     paquet
    -0.69
    Hein
    -0.68
    pushButton
    -0.68
     zegt
    -0.68
    siswa
    -0.68
    benhavn
    -0.67
    POSITIVE LOGITS
    randall
    0.85
     FA
    0.78
    blo
    0.77
    VL
    0.74
    FA
    0.73
     Christy
    0.73
     Highland
    0.73
     bladder
    0.72
     Wald
    0.70
    objc
    0.70
    Activations Density 0.020%

    No Known Activations