© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2391
    Prev
    Next
    INDEX
    Explanations

    Lung Cancer

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

    programming code elements, particularly class fields and properties in object-oriented code.

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

    This neuron fires strongly on numeric tokens—i.e. sequences of digits like literal numbers, version numbers, IDs, etc.

    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
    ઘ
    -0.84
     FURNITURE
    -0.80
    Bahkan
    -0.80
    冏
    -0.79
    合って
    -0.79
    tulo
    -0.79
     wartawan
    -0.77
    تاريخ
    -0.77
     ibang
    -0.77
     даже
    -0.74
    POSITIVE LOGITS
     version
    0.97
     status
    0.95
    isons
    0.93
    oredCriteria
    0.93
    del
    0.92
     state
    0.91
    isValid
    0.88
    status
    0.88
    Del
    0.87
     Del
    0.86
    Activations Density 0.005%

    No Known Activations