© 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. 66036
    Prev
    Next
    INDEX
    Explanations

    bright visual descriptors and names

    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
     refineries
    -0.79
    tente
    -0.74
     évek
    -0.73
     Fines
    -0.72
     talkin
    -0.72
    タク
    -0.71
     mcc
    -0.71
    なりに
    -0.69
     mellett
    -0.68
    画面
    -0.68
    POSITIVE LOGITS
    皰
    0.85
     dazzling
    0.83
     cervello
    0.80
     Gries
    0.76
    Ingestion
    0.75
     colectivos
    0.75
     trenes
    0.73
     земля
    0.73
    aggregated
    0.73
     sparkling
    0.72
    Activations Density 0.008%

    No Known Activations