© 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. 115628
    Prev
    Next
    INDEX
    Explanations

    programming code and urls

    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
    Vaata
    -0.87
    Good
    -0.73
    prechung
    -0.73
     granting
    -0.72
    typeparam
    -0.71
     polícia
    -0.71
    歌詞
    -0.71
    cieux
    -0.70
     Good
    -0.70
    鹼
    -0.70
    POSITIVE LOGITS
     nameof
    0.88
     Karachi
    0.81
     Senator
    0.79
    ruitment
    0.78
     Анато
    0.77
    zboi
    0.77
    ButtonStyle
    0.75
     Pakistan
    0.75
     Virginia
    0.74
     SEN
    0.74
    Activations Density 0.000%

    No Known Activations