© 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. 50324
    Prev
    Next
    INDEX
    Explanations

    connecting react-redux

    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
    embols
    -0.90
    飼
    -0.85
    Lying
    -0.78
    Thomson
    -0.77
    ിയ
    -0.77
     costas
    -0.77
    Druck
    -0.76
     respondents
    -0.75
    ErrorException
    -0.75
     **/
    
    -0.73
    POSITIVE LOGITS
     connect
    1.57
    connect
    1.34
     Connect
    1.33
    Connect
    1.28
     connection
    1.17
     connecting
    1.16
    connecting
    1.09
    CONNECT
    1.09
     CONNECT
    1.06
    Connecting
    1.06
    Activations Density 0.004%

    No Known Activations