© 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. 84800
    Prev
    Next
    INDEX
    Explanations

    syndicate, syndication, syndrom, syndactyly

    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
    kto
    -0.79
     домов
    -0.75
     Handle
    -0.73
    ↗
    -0.73
    derd
    -0.73
    letons
    -0.72
    hiza
    -0.72
    happy
    -0.72
     Georgetown
    -0.71
    huge
    -0.71
    POSITIVE LOGITS
     synd
    1.06
     Synd
    0.98
     syndicate
    0.95
    Synd
    0.93
     Sind
    0.84
     Dosto
    0.82
    Sind
    0.82
    はこちらから
    0.78
     стру
    0.77
     syndic
    0.76
    Activations Density 0.038%

    No Known Activations