© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49743
    Prev
    Next
    INDEX
    Explanations

    Cox proportional hazard

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

    programming and software license related content in code files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects license URL components—especially the domain parts (like “www”, “apache”) and version numbers in license URLs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     kolorze
    -0.76
     Viva
    -0.73
    黒
    -0.72
     Вар
    -0.71
     Oce
    -0.71
    ầu
    -0.70
     Intuition
    -0.69
    Residents
    -0.68
    די
    -0.68
    Nissan
    -0.68
    POSITIVE LOGITS
    AGENDA
    0.83
    bst
    0.79
     Taipei
    0.78
    mrt
    0.77
    ұл
    0.76
    INTAIN
    0.75
     couper
    0.73
     Ferien
    0.73
    updater
    0.72
     Kommunikations
    0.72
    Activations Density 0.006%

    No Known Activations