© 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. 107592
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

    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
     only
    -0.88
     additionally
    -0.76
    haikusbot
    -0.75
     nghiệp
    -0.75
    アプローチ
    -0.74
    同時に
    -0.73
     sodio
    -0.72
    <0xA3>
    -0.71
     prises
    -0.71
     linkages
    -0.71
    POSITIVE LOGITS
     miRNA
    0.92
    少し
    0.85
    ће
    0.83
    recyclerview
    0.81
    ticia
    0.79
     russischen
    0.79
     материа
    0.79
    anzug
    0.77
    cação
    0.77
    Tire
    0.76
    Activations Density 0.011%

    No Known Activations