© 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. 48000
    Prev
    Next
    INDEX
    Explanations

    closing and opening brackets

    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
     jsonString
    -0.82
     those
    -0.79
     [][]
    -0.77
     specifically
    -0.76
     carpenter
    -0.74
    =?";
    -0.72
     noin
    -0.72
     what
    -0.71
     with
    -0.70
    isNotEmpty
    -0.68
    POSITIVE LOGITS
    /"
    0.96
    <'
    0.91
    Harbor
    0.90
     "";
    0.88
     edificios
    0.86
     gimnasio
    0.84
    โปร
    0.82
     seguras
    0.82
     potty
    0.82
     lousy
    0.81
    Activations Density 0.065%

    No Known Activations