© 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. 76292
    Prev
    Next
    INDEX
    Explanations

    HTML links and icons

    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
    titude
    -0.76
     NKC
    -0.75
     nobly
    -0.75
     ۲۰۰
    -0.75
    hept
    -0.74
    urati
    -0.73
     outono
    -0.72
    putExtra
    -0.72
     Dolphin
    -0.72
    RESH
    -0.71
    POSITIVE LOGITS
    solicited
    0.85
    bashrc
    0.81
    ्रीय
    0.78
     atento
    0.78
    mercado
    0.78
     abends
    0.77
    ataa
    0.77
     Twitter
    0.76
     connections
    0.75
     sequences
    0.75
    Activations Density 0.014%

    No Known Activations