© 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. 10-GEMMASCOPE-RES-131K
    4. 10302
    Prev
    Next
    INDEX
    Explanations

    USB ports and cables

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "USB" followed by technical terms like "port", version numbers, or connection-related words in hardware/technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     juſ
    -2.13
    荭
    -1.83
    
    -1.77
     they
    -1.75
    撄
    -1.63
    を使用した
    -1.63
     também
    -1.62
     diki
    -1.61
     meur
    -1.57
     två
    -1.56
    POSITIVE LOGITS
    with
    2.28
    From
    1.74
     fairly
    1.70
     娘
    1.60
     должна
    1.56
    鯓
    1.56
    because
    1.52
    When
    1.51
    谈判
    1.48
    ోగ
    1.48
    Activations Density 0.010%

    No Known Activations