Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7689
    Prev
    Next
    INDEX
    Explanations

    network packet capture and traffic

    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
    ύ
    -0.93
    aneers
    -0.84
     recinto
    -0.83
    censo
    -0.81
     updater
    -0.81
     gardien
    -0.81
     visites
    -0.81
    antor
    -0.79
     mø
    -0.77
    semver
    -0.77
    POSITIVE LOGITS
     capture
    1.88
     capturing
    1.72
     captured
    1.71
    capture
    1.57
     captures
    1.55
     Capture
    1.38
     replay
    1.29
     analysis
    1.26
    Capture
    1.25
    dump
    1.24
    Activations Density 0.068%

    No Known Activations