© 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. 69829
    Prev
    Next
    INDEX
    Explanations

    data selection and preparation

    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
    isak
    -0.86
    uterte
    -0.84
    auger
    -0.81
     nieuwe
    -0.80
    СП
    -0.78
     костю
    -0.76
    président
    -0.76
    共产党
    -0.73
     gạch
    -0.73
    TJ
    -0.72
    POSITIVE LOGITS
    Coaching
    0.82
    予備
    0.82
     SCAN
    0.82
     prep
    0.81
     scanners
    0.78
    瑁
    0.75
    .");
    
    0.74
     preparation
    0.74
    ennas
    0.73
     Lard
    0.73
    Activations Density 0.001%

    No Known Activations