© 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. 38391
    Prev
    Next
    INDEX
    Explanations

    question prefixes and categories

    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
    ävän
    -0.83
    inicial
    -0.80
    setColor
    -0.79
     sichere
    -0.77
     it
    -0.76
    ijų
    -0.76
     jednak
    -0.75
    BCF
    -0.75
     entsch
    -0.74
     elég
    -0.73
    POSITIVE LOGITS
    resto
    0.81
     dată
    0.81
    atrième
    0.76
    شهاد
    0.75
    בד
    0.75
    Ilustra
    0.73
    shadowOffset
    0.73
    rena
    0.73
    мени
    0.72
    Passo
    0.71
    Activations Density 0.003%

    No Known Activations